© 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. 15207
    Prev
    Next
    INDEX
    Explanations

    indicates, investigate, Mix, less

    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
     Splash
    0.46
    ございます
    0.44
     Buffer
    0.43
     splashes
    0.41
     Rave
    0.41
    dwyd
    0.40
    ،
    0.40
     আচ্ছ
    0.40
     Prepar
    0.39
     Indica
    0.39
    POSITIVE LOGITS
    А
    0.49
    Why
    0.48
    How
    0.47
    Couldn
    0.47
    ام
    0.46
    Muy
    0.46
    Allen
    0.45
    COVID
    0.45
    ה
    0.45
    Overall
    0.44
    Activations Density 0.000%

    No Known Activations