© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251898
    Prev
    Next
    INDEX
    Explanations

    common phrases start

    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
    𝘔
    0.44
    ર્ચ
    0.42
    מן
    0.41
    ม
    0.41
    ц
    0.40
    서는
    0.39
    ᅱ
    0.39
    <0xEA>
    0.39
     南
    0.39
    зар
    0.39
    POSITIVE LOGITS
     khaki
    0.47
    glasses
    0.46
     generales
    0.46
     qualcosa
    0.46
     pessoais
    0.46
     doigts
    0.45
     destinés
    0.45
     peralatan
    0.45
     mangiare
    0.45
     récupération
    0.44
    Activations Density 0.001%

    No Known Activations