© 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. 33598
    Prev
    Next
    INDEX
    Explanations

    specific actions or states

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

    fortress and jacket

    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
     Kyng
    0.48
     Leitung
    0.46
     participa
    0.45
     bap
    0.45
     thước
    0.43
     recib
    0.42
     oni
    0.42
     b
    0.42
     correspondant
    0.42
     kinemat
    0.42
    POSITIVE LOGITS
    ForgotPassword
    0.51
     ਗ
    0.50
    glad
    0.50
    荳
    0.50
     ਵੀ
    0.50
     والم
    0.49
    滖
    0.49
     ignore
    0.49
    uacao
    0.48
    Toggle
    0.48
    Activations Density 0.000%

    No Known Activations