© 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. 136362
    Prev
    Next
    INDEX
    Explanations

    friends, horse, right

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

    sexual acts refused

    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
    佤
    0.50
    ня
    0.48
     Ичиго
    0.48
     величе
    0.48
    <unused188>
    0.45
    <unused2068>
    0.45
    Влади
    0.45
    迋
    0.45
    𝐘
    0.45
     nhằm
    0.44
    POSITIVE LOGITS
     electric
    0.48
     conformal
    0.47
     neurological
    0.45
     f
    0.44
     diagonal
    0.44
     steroid
    0.43
     neuron
    0.42
     steroids
    0.42
     anthrop
    0.42
     mitotic
    0.42
    Activations Density 0.000%

    No Known Activations