© 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-65K
    7. 4654
    Prev
    Next
    INDEX
    Explanations

    geometric dimensions and measurements

    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_65k_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
    uana
    0.47
    ahydro
    0.43
    awatir
    0.43
     poważ
    0.42
     তারা
    0.42
     הח
    0.42
    慑
    0.41
     đoán
    0.41
     गंभीरता
    0.41
    <unused985>
    0.41
    POSITIVE LOGITS
     size
    0.64
    大きさ
    0.58
     width
    0.54
     length
    0.53
     thickness
    0.48
    装着
    0.47
    长度
    0.46
    size
    0.46
    length
    0.44
    ขนาด
    0.44
    Activations Density 0.020%

    No Known Activations