© 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. 64532
    Prev
    Next
    INDEX
    Explanations

    roles and privacy

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

    analysis of elements

    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
     me
    0.56
     roto
    0.51
     bici
    0.50
    筏
    0.50
     Suz
    0.49
     râ
    0.47
     body
    0.47
     MZ
    0.47
     tens
    0.46
     rayon
    0.46
    POSITIVE LOGITS
    Making
    0.46
    J
    0.46
     Leveraging
    0.44
     Targeting
    0.44
     determining
    0.43
    ==============]
    0.43
     해서
    0.42
    determination
    0.40
     Making
    0.40
    talent
    0.40
    Activations Density 0.000%

    No Known Activations