© 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. 170061
    Prev
    Next
    INDEX
    Explanations

    product line

    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
     Rund
    0.52
     sauces
    0.50
     Etr
    0.49
    ๗
    0.48
     setbacks
    0.48
     Evers
    0.47
     Ook
    0.46
     provident
    0.46
     ово
    0.46
     Tricks
    0.46
    POSITIVE LOGITS
    ющем
    0.50
    n
    0.49
    der
    0.43
    Simulation
    0.43
     القسمه
    0.43
    collide
    0.42
    所有人
    0.41
    Acceleration
    0.41
    Deletion
    0.41
    жное
    0.41
    Activations Density 0.000%

    No Known Activations