© 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. 56757
    Prev
    Next
    INDEX
    Explanations

    heading, section titles, terms for repetition

    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
    umsal
    0.48
    amiento
    0.47
    gled
    0.44
    -
    0.44
    et
    0.43
     शिवा
    0.43
    hel
    0.42
    하며
    0.42
     అను
    0.41
    !!!!
    0.40
    POSITIVE LOGITS
     terakhir
    0.46
     minimising
    0.44
     consegn
    0.44
     trasmissione
    0.41
     pranzo
    0.41
     transferência
    0.40
    滔
    0.40
    耺
    0.40
     altri
    0.40
     debounce
    0.40
    Activations Density 0.010%

    No Known Activations