© 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. 13086
    Prev
    Next
    INDEX
    Explanations

    underscored the importance

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

    possession and strategic access

    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
    㬹
    0.47
    🏘
    0.46
    പ്പോഴും
    0.45
    钀
    0.44
     пай
    0.44
     വരു
    0.44
     విద్య
    0.44
    విద్య
    0.44
    场的
    0.44
    쁩
    0.43
    POSITIVE LOGITS
     aviso
    0.49
     voiced
    0.48
     apertura
    0.48
     antecedentes
    0.48
     envisions
    0.47
     alerta
    0.47
     naturale
    0.47
    であれば
    0.47
     asserts
    0.46
     traversed
    0.46
    Activations Density 0.001%

    No Known Activations