© 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. 129342
    Prev
    Next
    INDEX
    Explanations

    office building and real estate information

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

    serial communication

    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
    ﺎ
    0.50
    ản
    0.49
    apm
    0.47
    inicio
    0.46
    ío
    0.46
    sortie
    0.45
     বড়
    0.45
    िक
    0.44
    mensaje
    0.44
    撤
    0.44
    POSITIVE LOGITS
     pivots
    0.54
     stabilit
    0.53
     raat
    0.51
     attenu
    0.49
     krom
    0.49
     oxid
    0.48
     value
    0.48
     waarde
    0.48
     alfabet
    0.47
     OWN
    0.47
    Activations Density 0.000%

    No Known Activations