© 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. 113018
    Prev
    Next
    INDEX
    Explanations

    physical space descriptions

    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
     நிறை
    0.53
     Amp
    0.45
    pper
    0.44
    飥
    0.43
    psych
    0.43
    欱
    0.42
    Amino
    0.41
     cyclin
    0.41
     ע
    0.41
     Intake
    0.40
    POSITIVE LOGITS
    शाही
    0.56
     sofas
    0.47
     yada
    0.46
     smoky
    0.45
     consolation
    0.44
    哪怕
    0.44
     barges
    0.44
     suaves
    0.44
     dreamy
    0.43
     permisos
    0.43
    Activations Density 0.001%

    No Known Activations