© 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. 166189
    Prev
    Next
    INDEX
    Explanations

    Video Tutorial

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

    male pronoun sexual context

    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
    target
    0.61
    l
    0.54
    forward
    0.53
    lut
    0.53
    wor
    0.52
    モダン
    0.52
    but
    0.51
    pure
    0.51
    fins
    0.51
    lip
    0.51
    POSITIVE LOGITS
    渕
    0.54
     ngoài
    0.49
     vacation
    0.49
     erreichen
    0.48
     compara
    0.48
     serviço
    0.47
     conex
    0.47
    هایی
    0.47
     syslog
    0.47
    思维
    0.46
    Activations Density 0.000%

    No Known Activations