© 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. 194478
    Prev
    Next
    INDEX
    Explanations

    deliver us from evil

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

    resistance, capacity, issues

    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
     sighted
    0.47
     STAR
    0.45
     congress
    0.45
     published
    0.44
     stell
    0.44
     '*
    0.43
     tersebut
    0.42
     विवरण
    0.41
     parece
    0.41
    aris
    0.40
    POSITIVE LOGITS
     感
    0.52
    ール
    0.51
    Ideas
    0.47
    르
    0.47
    澶
    0.47
     Ideen
    0.46
     adres
    0.46
    AutoScale
    0.45
    FirebaseAuth
    0.45
    Anne
    0.45
    Activations Density 0.001%

    No Known Activations