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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104419
    Prev
    Next
    INDEX
    Explanations

    locations or contexts

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

    categorize distinguish identify models education DNA general main extreme

    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
    Not in Any Lists

    No Comments

    Negative Logits
     FLOR
    0.50
     FreeBSD
    0.46
     التج
    0.45
     cany
    0.44
    Flor
    0.44
    쐞
    0.44
    Centro
    0.44
    Tas
    0.44
    氬
    0.43
    верну
    0.43
    POSITIVE LOGITS
    ancer
    0.47
     yapar
    0.46
     fikir
    0.44
     mesela
    0.43
    amping
    0.43
     personnage
    0.42
     merasakan
    0.42
    acy
    0.41
    ylate
    0.41
     worsens
    0.41
    Activations Density 0.000%

    No Known Activations