© 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. 31794
    Prev
    Next
    INDEX
    Explanations

    too much, to jail

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

    ordering other things

    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
     opaque
    0.51
     grounded
    0.46
    ，
    0.46
     unspecified
    0.45
     embodied
    0.43
     ইনস্ট
    0.42
     Ground
    0.41
     instanceof
    0.41
     seated
    0.41
     incubated
    0.41
    POSITIVE LOGITS
     других
    0.47
    ގައި
    0.47
    OTHER
    0.47
    LLCATS
    0.46
    谴
    0.46
     інші
    0.46
     الأخرى
    0.46
     другие
    0.46
    ૦
    0.46
     другим
    0.45
    Activations Density 0.000%

    No Known Activations