© 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. 88368
    Prev
    Next
    INDEX
    Explanations

    mobile applications and services

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

    effects and vulnerabilities

    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
    오
    0.49
    örm
    0.45
    세계
    0.45
    ساز
    0.44
    屇
    0.44
    畐
    0.44
    கு
    0.44
    வு
    0.44
    纰
    0.43
    ினி
    0.42
    POSITIVE LOGITS
     Handicap
    0.54
    रिडोर
    0.53
    ;
    0.52
     eased
    0.52
     especificar
    0.50
     llrp
    0.50
    ]),
    0.49
     rs
    0.49
    fei
    0.48
     msg
    0.48
    Activations Density 0.000%

    No Known Activations