© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 27935
    Prev
    Next
    INDEX
    Explanations

    academic achievements

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

    Static Bloom pulsed

    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
    \
    0.44
     adjacency
    0.43
    -\
    0.43
    :\
    0.43
    Из
    0.43
    この
    0.42
    Have
    0.42
    にて
    0.42
    >::
    0.42
    你自己
    0.42
    POSITIVE LOGITS
     døde
    0.44
    socketState
    0.41
     errori
    0.41
     choisi
    0.41
    mousemove
    0.41
     changements
    0.41
    decorate
    0.40
    ಚ್ಚ
    0.40
    adaşlar
    0.40
    msg
    0.40
    Activations Density 0.000%

    No Known Activations