© 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. 31-GEMMASCOPE-2-RES-262K
    7. 38751
    Prev
    Next
    INDEX
    Explanations

    more, both, caught outdoors, modifications

    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
    ologically
    0.47
     Pakistani
    0.47
    Pak
    0.46
    戮
    0.44
    רי
    0.44
    qat
    0.43
    ashi
    0.43
     Nazis
    0.42
    GreaterThan
    0.42
    ícias
    0.42
    POSITIVE LOGITS
     cuire
    0.47
     separación
    0.46
     án
    0.45
    ἕ
    0.44
     ejecución
    0.43
     receber
    0.43
     eerder
    0.43
     separations
    0.43
     expérience
    0.43
     élevée
    0.42
    Activations Density 0.006%

    No Known Activations