© 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. 231724
    Prev
    Next
    INDEX
    Explanations

    as it

    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
     autonomic
    0.53
     love
    0.51
    love
    0.46
     那
    0.45
     NGOs
    0.44
     injunction
    0.44
    ঙে
    0.44
    自治
    0.43
     ASIC
    0.43
    阳光
    0.43
    POSITIVE LOGITS
     тоже
    0.52
    としての
    0.45
    か
    0.44
    fptr
    0.44
     janu
    0.43
    也會
    0.43
    Frontend
    0.42
     kuna
    0.42
    もあります
    0.42
    ぶり
    0.41
    Activations Density 0.002%

    No Known Activations