© 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. 228210
    Prev
    Next
    INDEX
    Explanations

    criminal justice, laws, rules

    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
    틱
    0.49
    Forgery
    0.47
    SdkError
    0.45
    境内
    0.44
    ან
    0.44
    вини
    0.43
    ენ
    0.43
    فين
    0.43
    ParaName
    0.43
    эл
    0.42
    POSITIVE LOGITS
     C
    0.47
     October
    0.44
     第一
    0.44
     oppressive
    0.41
     about
    0.41
     we
    0.40
     Cretaceous
    0.40
     September
    0.39
     Adult
    0.39
     -
    0.39
    Activations Density 0.000%

    No Known Activations