© 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. 221639
    Prev
    Next
    INDEX
    Explanations

    life, rights, suffering

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

    probability that a customer or any unit will take action

    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
     jų
    0.51
    milliseconds
    0.48
     Mã
    0.48
    𒆷
    0.47
    ㄼ
    0.46
     senere
    0.46
    𒄷
    0.46
     Tabla
    0.46
    毒
    0.45
    imcoords
    0.45
    POSITIVE LOGITS
    йтесь
    0.46
    www
    0.42
     jurispr
    0.41
     www
    0.40
     actual
    0.39
     entrepreneur
    0.39
     основ
    0.39
    青山
    0.39
    ích
    0.39
    うち
    0.39
    Activations Density 0.000%

    No Known Activations