© 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. 105701
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or events

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

    lists or enumeration

    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
    τεί
    0.52
    变
    0.52
    و
    0.50
    де
    0.44
    డే
    0.44
    过程中
    0.44
    Triangle
    0.43
     Chud
    0.42
    grad
    0.42
    溝
    0.42
    POSITIVE LOGITS
     fabrica
    0.52
     victimization
    0.49
     automatique
    0.48
     publica
    0.48
     espos
    0.48
    iería
    0.48
     automático
    0.48
    idamente
    0.47
     elimina
    0.47
     indictment
    0.46
    Activations Density 0.001%

    No Known Activations