© 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. 251899
    Prev
    Next
    INDEX
    Explanations

    March update

    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
     уто
    0.52
     乗
    0.52
    チュ
    0.50
     اك
    0.50
    有効
    0.50
     പ്രത്യേ
    0.50
    少なくとも
    0.50
     ሙ
    0.49
     特に
    0.49
     પો
    0.49
    POSITIVE LOGITS
    en
    0.59
     be
    0.57
    ya
    0.50
    et
    0.47
    canon
    0.46
     personaje
    0.45
     apellido
    0.45
     Gotta
    0.45
    ets
    0.45
    oh
    0.44
    Activations Density 0.001%

    No Known Activations