© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100607
    Prev
    Next
    INDEX
    Explanations

    online presence and discussions

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

    headlines or baby digital vitamins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reconsideration
    0.46
     දී
    0.46
     authorship
    0.45
     prudence
    0.44
     دیے
    0.44
    CompliancePolicy
    0.44
    ByID
    0.43
    .].
    0.42
    .
    0.41
    深い
    0.41
    POSITIVE LOGITS
     digitalen
    0.45
     BABY
    0.45
     Lets
    0.45
    冴
    0.44
     is
    0.43
     baby
    0.43
     titulares
    0.43
    ក
    0.42
     Ethereum
    0.42
    或者是
    0.42
    Activations Density 0.003%

    No Known Activations