© 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. 1911
    Prev
    Next
    INDEX
    Explanations

    multiples and squares

    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
     wszel
    0.47
    㝒
    0.46
    
    0.46
    实在是
    0.46
    珹
    0.46
     სპეცი
    0.45
     unapolog
    0.44
    阊
    0.44
    <unused392>
    0.43
    从来
    0.43
    POSITIVE LOGITS
    3
    0.69
    6
    0.66
    5
    0.65
    7
    0.61
    4
    0.61
    2
    0.59
    0.57
    1
    0.55
    9
    0.54
     twice
    0.54
    Activations Density 0.053%

    No Known Activations