© 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. 236095
    Prev
    Next
    INDEX
    Explanations

    maniac killer, trying to, health insurance

    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
    Runner
    0.47
    C
    0.46
     '
    0.45
     اشک
    0.43
     ภาพ
    0.42
     Motorcycle
    0.42
     フラ
    0.41
    BB
    0.40
    B
    0.40
     ଭ
    0.40
    POSITIVE LOGITS
     histó
    0.52
     espaços
    0.50
     personnalité
    0.49
    انا
    0.48
     centimet
    0.48
     localização
    0.48
     essentiel
    0.47
     esetben
    0.47
    دى
    0.46
     avantages
    0.46
    Activations Density 0.000%

    No Known Activations