© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4207
    Prev
    Next
    INDEX
    Explanations

    `bs` toggles, `vast` descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    0.56
     the
    0.51
     piezas
    0.50
    izarra
    0.50
     całym
    0.48
     asper
    0.48
     f
    0.45
     instrumentos
    0.43
    જરા
    0.42
    楽器
    0.42
    POSITIVE LOGITS
    Pens
    1.50
     hton
    1.46
     Eas
    1.41
    ранже
    1.40
    канчи
    1.37
     آورد
    1.35
    кат
    1.34
    authState
    1.33
    Won
    1.33
    -$\
    1.33
    Activations Density 0.025%

    No Known Activations