© 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. 25960
    Prev
    Next
    INDEX
    Explanations

    represents keys or dimensions

    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
    ുകൂ
    0.44
    ሉት
    0.41
    <unused21>
    0.40
    скет
    0.39
     Racer
    0.38
    áh
    0.38
    ગ
    0.38
    戽
    0.38
     رک
    0.37
     tê
    0.37
    POSITIVE LOGITS
    represents
    0.75
     represents
    0.73
     represent
    0.73
     representando
    0.64
     representar
    0.61
     representing
    0.61
     Represents
    0.60
    representing
    0.59
    represent
    0.59
     REPRESENT
    0.57
    Activations Density 0.083%

    No Known Activations