© 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. 81667
    Prev
    Next
    INDEX
    Explanations

    directly manipulating, range of

    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
     anticipation
    0.48
    erical
    0.47
     gastric
    0.44
    _{*}(
    0.42
    tail
    0.42
    abolic
    0.41
     ulcers
    0.41
    coil
    0.40
     spirals
    0.40
     strides
    0.40
    POSITIVE LOGITS
    ཋ
    0.49
     nascita
    0.46
    creating
    0.46
    Ꮔ
    0.46
     ಹುಡು
    0.46
     இரண்டாவது
    0.45
    initializeApp
    0.45
     papá
    0.45
     mamá
    0.44
    ে
    0.44
    Activations Density 0.002%

    No Known Activations