© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17359
    Prev
    Next
    INDEX
    Explanations

    path.join

    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_16_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
     or
    0.78
    ד
    0.70
    ya
    0.66
    一种
    0.63
    pl
    0.62
     and
    0.61
    dow
    0.60
    det
    0.59
    ش
    0.57
     as
    0.57
    POSITIVE LOGITS
    は
    0.76
    ﻮ
    0.74
    ین
    0.70
    er
    0.68
    Roasted
    0.65
    était
    0.65
    옥
    0.64
    cą
    0.64
     celebró
    0.64
    터를
    0.64
    Activations Density 0.004%

    No Known Activations