© 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. 8046
    Prev
    Next
    INDEX
    Explanations

    describing actions or usage

    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
     」,
    0.50
     этом
    0.49
     :,
    0.46
    இந்த
    0.46
     Audiobook
    0.46
    idän
    0.45
    ان
    0.44
     ():
    0.44
     οποία
    0.43
    School
    0.43
    POSITIVE LOGITS
    nya
    0.57
    ți
    0.57
    ct
    0.48
     sido
    0.48
    ные
    0.48
    ный
    0.46
    pping
    0.46
    bf
    0.46
    的和
    0.46
    様な
    0.45
    Activations Density 0.246%

    No Known Activations