© 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. 117593
    Prev
    Next
    INDEX
    Explanations

    suspicion or crime

    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
     T
    0.46
     M
    0.44
     H
    0.44
     V
    0.44
     C
    0.42
     S
    0.41
     Q
    0.40
    0.40
     data
    0.40
     CH
    0.40
    POSITIVE LOGITS
     indign
    0.43
    离婚
    0.42
    价值观
    0.41
    反对
    0.40
     వివా
    0.39
    违
    0.39
    性别
    0.39
    戕
    0.39
     अपमान
    0.38
    悯
    0.38
    Activations Density 1.199%

    No Known Activations