© 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. 13515
    Prev
    Next
    INDEX
    Explanations

    generating data and features

    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
     కుటుంబ
    0.33
    哽
    0.32
     ജില്ലാ
    0.32
    枓
    0.32
    開心
    0.31
     कर्मचारियों
    0.30
    ல்கள்
    0.30
    プレミア
    0.30
     veřej
    0.30
     meninggal
    0.29
    POSITIVE LOGITS
     the
    0.52
    Use
    0.38
    the
    0.37
    _
    0.37
    opy
    0.37
     utilizzare
    0.36
    -
    0.36
     those
    0.36
     mesh
    0.35
     there
    0.34
    Activations Density 0.000%

    No Known Activations