© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201167
    Prev
    Next
    INDEX
    Explanations

    information retrieval examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marco
    0.46
     dlatego
    0.46
    Marco
    0.44
     വിവര
    0.43
     PVC
    0.43
     Heating
    0.41
    foto
    0.41
     I
    0.40
     Because
    0.40
    telefone
    0.40
    POSITIVE LOGITS
    ificaciones
    0.50
     instalaciones
    0.45
     spectacularly
    0.44
     بیش
    0.41
     propias
    0.41
     extinguished
    0.41
    CISE
    0.40
     spectacular
    0.39
     regalos
    0.39
     fácilmente
    0.39
    Activations Density 0.002%

    No Known Activations