© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112174
    Prev
    Next
    INDEX
    Explanations

    mythical goddess, mystery novel, good friends

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

    strict hygiene

    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
    ٸ
    0.54
    CHREIB
    0.51
    ◼
    0.51
    <unused736>
    0.50
     limitado
    0.50
     convenio
    0.50
     ஓடுப
    0.50
     cenderung
    0.50
     incompet
    0.50
     تحقیق
    0.50
    POSITIVE LOGITS
    ਾ
    0.53
    э
    0.51
    an
    0.50
     ജ
    0.45
    strength
    0.43
    spectra
    0.43
    paste
    0.43
    ੇ
    0.43
    ان
    0.42
    semantics
    0.42
    Activations Density 0.000%

    No Known Activations