© 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. 113301
    Prev
    Next
    INDEX
    Explanations

    immediately followed by why

    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
    Ver
    0.43
    U
    0.42
     בשנת
    0.39
    URE
    0.38
    Pul
    0.38
    भौ
    0.38
     हुए
    0.38
    affected
    0.37
    S
    0.37
    G
    0.37
    POSITIVE LOGITS
     scén
    0.52
     permettant
    0.50
     azienda
    0.50
     prepping
    0.49
     kompos
    0.49
     tuples
    0.47
     everytime
    0.46
     biznes
    0.46
     DataSet
    0.46
    pèce
    0.46
    Activations Density 0.005%

    No Known Activations