© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 28191
    Prev
    Next
    INDEX
    Explanations

    measures of time and returns

    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
    ü
    0.48
    </s>
    0.44
    iss
    0.43
    ori
    0.42
    i
    0.42
     realizations
    0.42
    umen
    0.42
    ees
    0.42
    шите
    0.42
    e
    0.42
    POSITIVE LOGITS
    高铁
    0.51
     Slav
    0.44
    zuführen
    0.44
     Patagonia
    0.44
     Zuid
    0.43
     reign
    0.43
    দ্ম
    0.43
     Straßen
    0.42
     óta
    0.42
     الجديد
    0.42
    Activations Density 0.000%

    No Known Activations