© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27197
    Prev
    Next
    INDEX
    Explanations

    here on or in places

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

    The neuron flags mentions of a location or platform (e.g. “here on SO,” “on Meta,” “in KL,” “here on the site”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    .=
    -1.28
     célébr
    -1.23
    鱨
    -1.14
    烀
    -1.13
    絎
    -1.10
     Vorschlag
    -1.10
     offrire
    -1.09
    来不及
    -1.09
    .***
    -1.08
    Sö
    -1.08
    POSITIVE LOGITS
     ‘
    1.34
    The
    1.23
    we
    1.16
     in
    1.15
    only
    1.13
     –
    1.13
     only
    1.13
     „
    1.12
    i
    1.10
    č
    1.07
    Activations Density 0.010%

    No Known Activations