© 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. 231559
    Prev
    Next
    INDEX
    Explanations

    suspenseful espionage thriller

    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
    ın
    0.48
    ίλ
    0.46
    U
    0.46
    ίν
    0.44
    িও
    0.44
    áveis
    0.43
    性价比
    0.43
    ing
    0.42
     Excited
    0.42
    诶
    0.41
    POSITIVE LOGITS
     horrifying
    0.49
     писатель
    0.46
     inescap
    0.45
     რომელი
    0.44
     Macmillan
    0.44
     traitor
    0.43
     blackmail
    0.43
     spowod
    0.43
     نار
    0.43
     horrors
    0.42
    Activations Density 0.000%

    No Known Activations