© 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. 154892
    Prev
    Next
    INDEX
    Explanations

    real estate claims

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

    numbers and lists

    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
    فك
    0.46
     estratégica
    0.46
    櫈
    0.44
    📆
    0.42
     estratégico
    0.42
     каб
    0.42
    💋
    0.42
     mâ
    0.41
     Dasar
    0.41
    ikovsky
    0.41
    POSITIVE LOGITS
    1
    0.50
    2
    0.50
    9
    0.48
    by
    0.48
    overview
    0.47
    できない
    0.46
    from
    0.46
    bly
    0.46
     दक्षिण
    0.44
    否
    0.43
    Activations Density 0.000%

    No Known Activations