© 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. 220076
    Prev
    Next
    INDEX
    Explanations

    specific entities and domains

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

    dominance and humiliation

    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
     程
    0.49
     fortement
    0.46
     operativo
    0.45
     നെറ്റ്‌വർ
    0.45
    ونکی
    0.44
     fréquente
    0.43
    STE
    0.43
     buildFor
    0.42
    熠
    0.42
    POST
    0.42
    POSITIVE LOGITS
    iv
    0.59
    0.55
     slaves
    0.54
     sound
    0.50
    ised
    0.49
     recordings
    0.49
    ieso
    0.48
    ),
    0.48
     vw
    0.47
    iously
    0.47
    Activations Density 0.000%

    No Known Activations