© 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. 246475
    Prev
    Next
    INDEX
    Explanations

    not hereditary, answer key, hire American

    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
     experimentos
    0.54
     β
    0.53
     tumours
    0.53
     aber
    0.51
    uestas
    0.51
    β
    0.51
     beber
    0.49
    isos
    0.49
     attended
    0.49
     $\
    0.48
    POSITIVE LOGITS
    جهة
    0.51
    ياة
    0.50
     لكل
    0.49
    指數
    0.48
    指数
    0.47
     Bhagavato
    0.45
    StringEncoding
    0.44
     دليل
    0.43
    中國
    0.42
     যেটা
    0.42
    Activations Density 0.000%

    No Known Activations