© 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. 165266
    Prev
    Next
    INDEX
    Explanations

    business and rentals

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

    implies consequences

    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
    ोसिएशन
    0.52
     हमला
    0.48
     attacked
    0.48
    珹
    0.47
     insulted
    0.46
     হামলা
    0.44
     സാധ
    0.43
    聒
    0.42
     zo
    0.40
    ುದ
    0.40
    POSITIVE LOGITS
     đôi
    0.46
     và
    0.46
    and
    0.45
     bây
    0.45
     và
    0.45
     jotka
    0.44
     którą
    0.44
    bae
    0.44
     laquelle
    0.43
    ப்பான
    0.43
    Activations Density 0.001%

    No Known Activations