© 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. 111641
    Prev
    Next
    INDEX
    Explanations

    simple specifications or descriptions

    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
    ወስ
    0.44
    德
    0.44
    嫦
    0.41
     cysteine
    0.40
    စေ
    0.38
    pèce
    0.38
     sauv
    0.38
    να
    0.38
    嗤
    0.38
    יל
    0.37
    POSITIVE LOGITS
    ̌
    0.48
    ().
    0.45
     Fractional
    0.45
     ingin
    0.42
     (${
    0.42
     Saya
    0.42
     கூடிய
    0.42
    ました
    0.41
     Lub
    0.40
     പുതിയ
    0.40
    Activations Density 0.009%

    No Known Activations