© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    ר
    0.80
    ر
    0.64
     incisions
    0.63
     rétrécies
    0.62
    র
    0.62
     erections
    0.61
     boulders
    0.60
     dentures
    0.59
    在
    0.59
     coste
    0.58
    POSITIVE LOGITS
    0
    0.98
    <0x80>
    0.85
    ️⃣
    0.83
    as
    0.76
    ak
    0.65
    za
    0.60
    af
    0.60
    ah
    0.59
    ie
    0.58
    kons
    0.57
    Activations Density 0.122%

    No Known Activations