© 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. 82132
    Prev
    Next
    INDEX
    Explanations

    common decryption disable

    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
    apel
    0.50
    Effect
    0.48
     інших
    0.47
     種
    0.47
    espèces
    0.46
    Plants
    0.46
     останов
    0.45
    Conservation
    0.45
    Map
    0.44
    Flora
    0.44
    POSITIVE LOGITS
    克服
    0.46
     tacit
    0.42
     detrás
    0.42
     reorgan
    0.42
     conglomer
    0.41
     comienzo
    0.41
     circost
    0.41
     reorganized
    0.41
    躬
    0.41
    ですが
    0.41
    Activations Density 0.003%

    No Known Activations