© 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. 42078
    Prev
    Next
    INDEX
    Explanations

    locking, touching, parameters, regularly, until, array

    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
     of
    0.58
    O
    0.48
    2
    0.45
    平台的
    0.44
    of
    0.43
     о
    0.43
    สนับสนุน
    0.42
    </sub>
    0.42
    </b>
    0.42
    Ken
    0.42
    POSITIVE LOGITS
    ڊ
    0.52
    कार्बन
    0.49
    وندی
    0.47
     charging
    0.46
    зё
    0.46
    ூ
    0.46
    ہی
    0.45
    charges
    0.45
    يند
    0.44
    蜞
    0.44
    Activations Density 0.001%

    No Known Activations