© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80104
    Prev
    Next
    INDEX
    Explanations

    Olympic, architectural, deal

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

    empty, economic, dynamic, disrespect, spilled

    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
     அனைத்தும்
    0.47
    kira
    0.46
     manuals
    0.46
    -----
    0.45
    cart
    0.45
     راحت
    0.45
    ttä
    0.45
    ------
    0.44
     furtherance
    0.44
    txtarea
    0.44
    POSITIVE LOGITS
    ลีก
    0.45
    гро
    0.43
    StatusOK
    0.42
     Lockdown
    0.41
    achadh
    0.41
    ولد
    0.41
     Wettbewer
    0.40
    却是
    0.40
    瑯
    0.40
    гас
    0.39
    Activations Density 0.001%

    No Known Activations