© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 49223
    Prev
    Next
    INDEX
    Explanations

    crafting malicious content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ceded
    0.41
     ಮಾತ್ರ
    0.40
    Cotton
    0.40
     తగ్గి
    0.40
     ANON
    0.40
     phi
    0.39
    ῴ
    0.39
    $...
    0.39
    λεκ
    0.38
    Blog
    0.38
    POSITIVE LOGITS
     präsentiert
    0.46
    ]);
    0.43
    aky
    0.43
    jing
    0.41
    logan
    0.41
     loading
    0.40
     ak
    0.40
     amarelo
    0.40
     ])
    0.39
     الأصفر
    0.39
    Activations Density 0.012%

    No Known Activations