Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12575
    Prev
    Next
    INDEX
    Explanations

    comes home

    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
     বলিয়াই
    0.43
    ٰذا
    0.40
    <unused984>
    0.40
     assass
    0.39
     Aby
    0.39
    <unused297>
    0.39
    ště
    0.39
    AnyCPU
    0.38
    相同
    0.37
    setVisible
    0.37
    POSITIVE LOGITS
    s
    0.50
     tatt
    0.48
     woord
    0.46
    decken
    0.43
    திக்க
    0.42
    talking
    0.42
    Milwaukee
    0.42
    rels
    0.42
    ঘাট
    0.42
    Cult
    0.41
    Activations Density 0.003%

    No Known Activations