© 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. 86783
    Prev
    Next
    INDEX
    Explanations

    secret matter compliment forces mates

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

    conspiracy, minimum, urine, impossibly, public

    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
     bırak
    0.53
    lara
    0.50
    ஐ
    0.49
    ایا
    0.49
    وتا
    0.47
    韦
    0.47
     nə
    0.47
    ්‍ය
    0.46
     risultati
    0.45
    addPreferredGap
    0.45
    POSITIVE LOGITS
    Serialized
    0.52
    PRODUCTION
    0.48
    Dimethyl
    0.47
    FK
    0.47
    ments
    0.46
    Volume
    0.46
    OIL
    0.44
    Unsupported
    0.43
     heavier
    0.43
    conjug
    0.42
    Activations Density 0.000%

    No Known Activations