© 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. 50589
    Prev
    Next
    INDEX
    Explanations

    planning and continuation

    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
    ula
    0.54
     transforms
    0.48
    ני
    0.47
     abort
    0.47
     தயாரி
    0.46
    pi
    0.46
    בו
    0.46
    ]#
    0.45
    RE
    0.45
    ্তন
    0.45
    POSITIVE LOGITS
    ného
    0.47
    Payout
    0.46
    拎
    0.46
    ispiele
    0.45
    maintained
    0.44
    čných
    0.44
    érios
    0.43
    hened
    0.42
    aço
    0.42
    étant
    0.42
    Activations Density 0.001%

    No Known Activations