© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 170070
    Prev
    Next
    INDEX
    Explanations

    research purposes, data array, Silhouette score

    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
     resear
    0.46
     well
    0.46
     prüfe
    0.44
    ∶
    0.44
     maintained
    0.43
    maintained
    0.42
     büyü
    0.42
     popul
    0.42
     čast
    0.42
     growth
    0.41
    POSITIVE LOGITS
    Circles
    0.56
    િન
    0.47
    AN
    0.45
    חר
    0.45
    姮
    0.45
    િય
    0.44
    螳
    0.44
    Якщо
    0.44
    Agregar
    0.43
    On
    0.43
    Activations Density 0.000%

    No Known Activations