© 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. 80824
    Prev
    Next
    INDEX
    Explanations

    actions and situations

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

    SPVs and metaphors

    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
    غا
    0.51
    <0x8D>
    0.50
     CHRISTIAN
    0.50
    cannot
    0.48
    ၶ
    0.47
    듦
    0.47
    נו
    0.47
    טן
    0.46
    <0xA0>
    0.46
    یا
    0.45
    POSITIVE LOGITS
     मशहूर
    0.50
    ?”,
    0.47
    限
    0.45
    raul
    0.45
     indol
    0.45
    empo
    0.43
     obstructing
    0.43
     داش
    0.42
     Mahall
    0.42
     embrace
    0.42
    Activations Density 0.001%

    No Known Activations