© 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. 3506
    Prev
    Next
    INDEX
    Explanations

    technical, future services

    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
    er
    0.51
    us
    0.49
    ැල
    0.45
    mittel
    0.43
    脆
    0.43
    切
    0.42
     respectfully
    0.42
     norme
    0.42
    ffekt
    0.41
    draw
    0.40
    POSITIVE LOGITS
     cay
    0.49
     espacios
    0.47
     каждой
    0.45
    Guitar
    0.45
     квартиры
    0.44
     armario
    0.44
     parvenir
    0.44
     jard
    0.43
    /}{
    0.43
     ordinateur
    0.43
    Activations Density 0.001%

    No Known Activations