© 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. 143511
    Prev
    Next
    INDEX
    Explanations

    .com domain names

    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
    í
    0.53
    I
    0.47
    ر
    0.46
    Calcul
    0.44
    je
    0.44
     एस
    0.43
     huk
    0.43
    ja
    0.43
    ه
    0.43
     oeste
    0.42
    POSITIVE LOGITS
    可能な
    0.51
     principally
    0.47
     fledgling
    0.46
    thisTrack
    0.45
     flexibly
    0.45
     GROUND
    0.45
    小型
    0.44
    হাব
    0.44
     squarely
    0.44
     microbial
    0.43
    Activations Density 0.004%

    No Known Activations