© 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. 30155
    Prev
    Next
    INDEX
    Explanations

    dimensions (e.g., 20x30)

    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
     to
    0.52
     Hz
    0.44
    sized
    0.41
     Telef
    0.40
     M
    0.40
     murid
    0.39
     _
    0.38
    bern
    0.38
     ತಿಳ
    0.38
    haram
    0.38
    POSITIVE LOGITS
     социа
    0.45
    ActionBar
    0.39
     useCallback
    0.39
     adequacy
    0.38
     службу
    0.38
    expec
    0.38
    }}^{*}
    0.38
    Availability
    0.38
    𒅀
    0.38
     સૌ
    0.37
    Activations Density 0.000%

    No Known Activations