© 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. 108400
    Prev
    Next
    INDEX
    Explanations

    descriptive categories

    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
     staffing
    0.43
    SKY
    0.43
    نان
    0.43
     Reginald
    0.43
     Seite
    0.42
    ید
    0.42
    ױ
    0.42
    音
    0.42
     Pipp
    0.41
     tomu
    0.41
    POSITIVE LOGITS
    bss
    0.46
    istics
    0.45
    apeutic
    0.44
    ist
    0.44
    burst
    0.43
    istu
    0.42
     wholes
    0.42
    (";
    0.42
    &#
    0.41
    alities
    0.41
    Activations Density 0.000%

    No Known Activations