© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20051
    Prev
    Next
    INDEX
    Explanations

    often competitive, comparable or significantly faster

    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
     मच्छर
    0.45
     fárm
    0.44
    Jadi
    0.44
     espécies
    0.44
    뿜
    0.44
    鳃
    0.43
     estándar
    0.42
     água
    0.42
    䐍
    0.42
     això
    0.42
    POSITIVE LOGITS
     statement
    0.44
    ''
    0.41
     deliberation
    0.41
    statement
    0.41
     precedent
    0.41
     Switzerland
    0.40
     fielding
    0.40
    gf
    0.39
     comment
    0.39
     world
    0.37
    Activations Density 0.019%

    No Known Activations