© 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. 62557
    Prev
    Next
    INDEX
    Explanations

    logical conditions

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

    language support or explanation

    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
     横
    0.52
     বৌদ্ধ
    0.49
     HOM
    0.48
     海
    0.48
     contigo
    0.47
    dois
    0.47
     morreu
    0.46
     permas
    0.46
     বুলেট
    0.46
     residuos
    0.46
    POSITIVE LOGITS
    )}}{\
    0.45
    뭘
    0.44
    anesh
    0.42
    તુ
    0.42
    లం
    0.42
    안녕하세요
    0.41
    čit
    0.41
    rą
    0.41
    acz
    0.41
    لان
    0.40
    Activations Density 0.000%

    No Known Activations