© 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. 184253
    Prev
    Next
    INDEX
    Explanations

    phrase

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

    negative thinking patterns

    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
     Police
    0.45
     Hz
    0.43
     Uncertain
    0.43
     Ai
    0.42
     Dairy
    0.41
     Violent
    0.41
     Mic
    0.41
    扫
    0.40
     ③
    0.40
     Grilled
    0.40
    POSITIVE LOGITS
    КС
    0.55
    SegmentInfo
    0.53
     confirmado
    0.49
     pennies
    0.48
     moderno
    0.47
    oslovens
    0.47
     mobilité
    0.47
    Clientes
    0.47
     viviendo
    0.46
     apartamentos
    0.46
    Activations Density 0.002%

    No Known Activations