© 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. 26866
    Prev
    Next
    INDEX
    Explanations

    strings of lights

    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
     család
    0.50
     കുടുംബ
    0.50
     sects
    0.49
    -]
    0.46
    se
    0.44
     schools
    0.44
    bloom
    0.44
     ගැන
    0.43
     INTO
    0.43
     Montag
    0.43
    POSITIVE LOGITS
    τη
    0.50
    ක්
    0.50
    ập
    0.48
    وس
    0.48
    ли
    0.48
    ή
    0.47
    ете
    0.47
    える
    0.47
    lée
    0.45
    ériques
    0.45
    Activations Density 0.001%

    No Known Activations