© 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. 113275
    Prev
    Next
    INDEX
    Explanations

    romantic outing

    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
     Henry
    0.48
    :
    0.43
    ;
    0.42
     Musicians
    0.40
     Captain
    0.39
     Mo
    0.39
     Gli
    0.39
     rebuild
    0.38
     Ltd
    0.38
    .
    0.38
    POSITIVE LOGITS
     خواست
    0.47
    ଘ
    0.46
    ቱም
    0.44
    Appl
    0.43
    bouquet
    0.43
    Appuntamento
    0.42
    什么的
    0.42
    मेलन
    0.41
     celebrar
    0.41
    خواست
    0.41
    Activations Density 0.012%

    No Known Activations