© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29165
    Prev
    Next
    INDEX
    Explanations

    bug bounty programs

    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_31_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
    ുവരി
    0.32
     էին
    0.30
    ಬ್ಬಿಣ
    0.29
     inhomogeneities
    0.29
    OLYBD
    0.29
    ሳሪያ
    0.29
    誣
    0.29
     contenir
    0.28
     myeloid
    0.28
     substituents
    0.27
    POSITIVE LOGITS
    -
    0.59
     and
    0.52
    ,
    0.49
     After
    0.46
    /
    0.46
    ↵
    0.45
     When
    0.45
    ↵↵
    0.44
    et
    0.42
     With
    0.41
    Activations Density 0.000%

    No Known Activations