© 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. 168822
    Prev
    Next
    INDEX
    Explanations

    thesis, score, minimize, turns, ABLE, Leaves, Brief

    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
    ‶
    0.55
    RELAND
    0.52
    YEAR
    0.51
     혹은
    0.49
    ᕈ
    0.48
     года
    0.47
     emeritus
    0.46
    AN
    0.45
    tahun
    0.45
    (
    0.45
    POSITIVE LOGITS
     water
    0.60
     tub
    0.51
     Nightmare
    0.49
     salt
    0.48
     stom
    0.48
     tube
    0.47
     total
    0.47
     tubig
    0.46
     calories
    0.46
     lipstick
    0.46
    Activations Density 0.004%

    No Known Activations