© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111289
    Prev
    Next
    INDEX
    Explanations

    this followed by that or it

    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
    ​,
    0.51
     शिलाजीत
    0.46
    뀜
    0.45
    бі
    0.45
    竻
    0.44
    بان
    0.44
    適合
    0.44
    结构
    0.44
    結構
    0.44
    ወቅ
    0.43
    POSITIVE LOGITS
     Nik
    0.43
    on
    0.42
     commemorate
    0.41
    utta
    0.39
    uire
    0.39
     Hare
    0.39
    ivi
    0.38
    .@
    0.38
     M
    0.38
    anam
    0.37
    Activations Density 0.008%

    No Known Activations