© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26819
    Prev
    Next
    INDEX
    Explanations

    some of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    žno
    -1.30
     horloge
    -1.29
    (++
    -1.29
     男の子
    -1.26
    🗿
    -1.24
    '--
    -1.23
    ivores
    -1.23
    💃
    -1.23
    かつ
    -1.22
     entièrement
    -1.22
    POSITIVE LOGITS
     things
    1.66
     wenigen
    1.44
     πιο
    1.41
     might
    1.40
     brilliantly
    1.38
     utwor
    1.34
     parts
    1.30
    }$.
    1.30
    几个
    1.30
     have
    1.29
    Activations Density 0.024%

    No Known Activations