Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169844
    Prev
    Next
    INDEX
    Explanations

    interchangeably, used with a following explanation

    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
     The
    0.48
     Luca
    0.45
    cere
    0.44
     ferocious
    0.44
     Cea
    0.44
     Derbyshire
    0.43
     незале
    0.43
     ယ
    0.42
     Sue
    0.41
    ecc
    0.41
    POSITIVE LOGITS
     gathered
    0.51
    вате
    0.48
    EndZ
    0.48
    idlertid
    0.45
     spawned
    0.44
    也能
    0.44
    开始
    0.44
    放在
    0.44
    できるように
    0.44
     voices
    0.43
    Activations Density 0.002%

    No Known Activations