© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112599
    Prev
    Next
    INDEX
    Explanations

    mailbox, outdoor, boxes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is strongly activated by words naming outdoor household fixtures or exterior attachments (e.g. “mailbox,” “porch,” “fences,” “steps”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gangen
    -1.43
    Viel
    -1.42
    ilige
    -1.35
     fjor
    -1.27
     hablado
    -1.27
     løpet
    -1.27
     EVEN
    -1.26
    ाउनलोड
    -1.25
     italianos
    -1.23
     éton
    -1.22
    POSITIVE LOGITS
     our
    1.52
     should
    1.32
     one
    1.21
    </i>
    1.16
     these
    1.15
    [...,
    1.15
     which
    1.13
     because
    1.13
     usati
    1.11
     like
    1.10
    Activations Density 0.049%

    No Known Activations