© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130175
    Prev
    Next
    INDEX
    Explanations

    website, page, share

    np_acts-logits-general · gemini-2.5-flash-lite

    release and relax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sparking
    0.50
    ه
    0.47
     shifts
    0.44
     contractile
    0.44
     θε
    0.43
     prosper
    0.43
     Αγ
    0.43
     carers
    0.43
    cedores
    0.41
     Μαρ
    0.41
    POSITIVE LOGITS
    チューブ
    0.48
    currentItem
    0.46
     بهذه
    0.46
    मिन
    0.45
    カイ
    0.45
    古い
    0.45
    å
    0.45
    toISO
    0.44
    connected
    0.44
    抻
    0.44
    Activations Density 0.000%

    No Known Activations