© 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. 143664
    Prev
    Next
    INDEX
    Explanations

    personal opinions or death

    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
     велико
    0.47
     be
    0.44
    ır
    0.43
     शब्दा
    0.43
     клави
    0.43
     повре
    0.42
     будь
    0.42
    <0xAD>
    0.41
     unimagin
    0.41
     применение
    0.41
    POSITIVE LOGITS
    ಸ್ಕೊ
    0.46
     austenite
    0.46
    otherArgs
    0.45
    續
    0.42
     uppercase
    0.42
    ㊗
    0.41
    dai
    0.41
    蛋糕
    0.41
    ിക്കും
    0.41
    zeko
    0.40
    Activations Density 0.014%

    No Known Activations