© 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-65K
    7. 20186
    Prev
    Next
    INDEX
    Explanations

    AI's purpose and limitations

    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_65k_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
    」「
    0.46
    </a>
    0.43
    to
    0.42
     Santiago
    0.41
    보
    0.41
     https
    0.40
    코
    0.40
     #
    0.40
     Perez
    0.40
     G
    0.40
    POSITIVE LOGITS
    Motivation
    0.54
    Celltype
    0.50
    avenir
    0.46
    YNAMICS
    0.46
    ড়ানো
    0.46
    Future
    0.45
    future
    0.45
     остальных
    0.45
    ONU
    0.44
    ULTURE
    0.44
    Activations Density 0.280%

    No Known Activations