© 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. 196937
    Prev
    Next
    INDEX
    Explanations

    For women, disputes, overall casting

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

    embracing absurdity or blocking content

    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
    ೀ
    0.43
    ionali
    0.43
    itling
    0.43
    म्भ
    0.41
    徠
    0.41
     inlet
    0.41
    Survivor
    0.41
     solusi
    0.40
    ══
    0.40
    সহ
    0.39
    POSITIVE LOGITS
     次
    0.46
    บา
    0.46
    锹
    0.45
     Lynn
    0.45
     Maureen
    0.45
    bersome
    0.44
     очередь
    0.44
     खासकर
    0.44
    รอบ
    0.44
     alanı
    0.43
    Activations Density 0.000%

    No Known Activations