© 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. 39940
    Prev
    Next
    INDEX
    Explanations

    internal damage

    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
     menace
    0.53
     עוד
    0.51
     கிடை
    0.49
    豬
    0.49
     squat
    0.47
     স্থান
    0.47
    міст
    0.47
     वारदात
    0.46
     নির্দিষ্ট
    0.46
     વૃક્ષ
    0.46
    POSITIVE LOGITS
    ith
    0.48
    da
    0.47
    or
    0.45
    c
    0.44
    ia
    0.41
    ik
    0.41
    is
    0.40
    um
    0.39
     dedicating
    0.38
    avacanam
    0.38
    Activations Density 0.013%

    No Known Activations