© 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. 16880
    Prev
    Next
    INDEX
    Explanations

    delimiting characters

    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
                          
    0.34
     casein
    0.34
     food
    0.31
    with
    0.31
     citrus
    0.31
     उन्हें
    0.31
    ơm
    0.30
     UIText
    0.30
    一
    0.30
                     
    0.30
    POSITIVE LOGITS
     seiner
    0.36
    }^{*}=
    0.36
     ไหร่
    0.35
    hebung
    0.34
     tehát
    0.33
     ჩატი
    0.33
    骢
    0.33
     yani
    0.33
     Notably
    0.33
    つまり
    0.33
    Activations Density 0.044%

    No Known Activations