© 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. 142002
    Prev
    Next
    INDEX
    Explanations

    linear model

    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
    ាច់
    0.58
    剂量
    0.57
     fift
    0.54
     রাজশ
    0.53
     faute
    0.53
    醾
    0.53
    无比
    0.52
     determinante
    0.52
    举
    0.52
    单一
    0.52
    POSITIVE LOGITS
     as
    0.68
     are
    0.68
    𝘃
    0.62
     a
    0.61
    roller
    0.61
    porters
    0.61
    p
    0.61
     ஆர்வ
    0.60
    Loc
    0.60
    adores
    0.58
    Activations Density 0.000%

    No Known Activations