© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2235
    Prev
    Next
    INDEX
    Explanations

    what one is capable of

    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_262k_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
    ли
    0.77
    ۹
    0.70
    ای
    0.65
    arquivo
    0.64
    ат
    0.62
    ່ວນ
    0.62
    К
    0.60
    இ
    0.59
    साठी
    0.59
    ੦
    0.59
    POSITIVE LOGITS
     withstand
    0.76
     ability
    0.65
     Ability
    0.63
    Ability
    0.62
    ;
    0.59
    ↵↵
    0.52
     способность
    0.52
    to
    0.52
     kemampuan
    0.51
     capability
    0.50
    Activations Density 0.035%

    No Known Activations