Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8355
    Prev
    Next
    INDEX
    Explanations

    VS Code, voice, Material

    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
     pInBuffer
    0.45
    (),
    0.44
    มีการ
    0.42
    _=
    0.41
    _',
    0.41
    手を
    0.41
    𝘥
    0.40
    厚生
    0.40
    ш
    0.40
    อก
    0.39
    POSITIVE LOGITS
     pinpoint
    0.42
     console
    0.42
     Jun
    0.41
     standout
    0.41
     wild
    0.40
     ባህ
    0.40
    youtu
    0.39
     service
    0.39
     Brandon
    0.39
     stability
    0.38
    Activations Density 0.004%

    No Known Activations