© 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. 100075
    Prev
    Next
    INDEX
    Explanations

    cloud gaming and development environments

    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
    and
    0.55
    0
    0.53
    at
    0.50
    for
    0.48
    <0x80>
    0.48
    2
    0.47
    as
    0.47
    or
    0.45
    まれ
    0.43
    ava
    0.41
    POSITIVE LOGITS
    起的
    0.51
     basée
    0.49
     ouverture
    0.48
     extremamente
    0.48
    няя
    0.47
     aides
    0.47
     identiques
    0.46
     trimmed
    0.46
    itively
    0.46
     buhay
    0.46
    Activations Density 0.001%

    No Known Activations