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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 5105
    Prev
    Next
    INDEX
    Explanations

    titles starting with punctuation

    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_40_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
    robespierre
    0.22
    跶
    0.22
     trialComponents
    0.21
    ስቃሴ
    0.21
     fluv
    0.21
     صہیون
    0.21
     ovipares
    0.20
     %``
    0.20
    vrage
    0.20
    礴
    0.20
    POSITIVE LOGITS
     The
    0.36
    The
    0.33
    the
    0.28
     A
    0.28
     City
    0.26
     M
    0.25
     Star
    0.25
     Into
    0.24
    H
    0.24
     I
    0.24
    Activations Density 0.034%

    No Known Activations