© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16334
    Prev
    Next
    INDEX
    Explanations

    based on patterns

    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
    assertArg
    0.45
    adhi
    0.44
    astotal
    0.44
    曜
    0.44
    atah
    0.44
     Prothorax
    0.43
    eqnarray
    0.43
    endpoint
    0.42
    גה
    0.42
     செய்யும்
    0.42
    POSITIVE LOGITS
    歉
    0.46
    বিষ্য
    0.44
     corrections
    0.44
     consequences
    0.43
    <strong>
    0.42
    TRO
    0.42
     conséquences
    0.42
     noises
    0.41
    薄
    0.41
     sneaky
    0.41
    Activations Density 0.012%

    No Known Activations