© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111338
    Prev
    Next
    INDEX
    Explanations

    Not the Model Itself

    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_40_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
    VIII
    0.42
     сопрово
    0.39
    swald
    0.39
     huit
    0.38
     Hagen
    0.38
    Guardian
    0.38
     গাঙ্গ
    0.38
    <0xDC>
    0.37
    GAAP
    0.36
     accompagner
    0.36
    POSITIVE LOGITS
     nourishing
    0.43
    职工
    0.41
     COc
    0.41
    รือ
    0.40
    MONTH
    0.39
    筞
    0.38
     affaires
    0.38
     prer
    0.37
    钅
    0.37
    哫
    0.37
    Activations Density 0.000%

    No Known Activations