© 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-65K
    7. 31208
    Prev
    Next
    INDEX
    Explanations

    preface, understand, checks, think, changing

    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_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
    ק
    0.56
    า
    0.55
    ση
    0.51
    ně
    0.50
    temperatur
    0.48
     nuestros
    0.46
     внимание
    0.46
    ב
    0.45
    бо
    0.45
    必须
    0.44
    POSITIVE LOGITS
     disaster
    0.49
     stares
    0.49
     starg
    0.48
     án
    0.48
    \$
    0.48
     spheres
    0.48
    :”
    0.47
     democratic
    0.46
     SSB
    0.46
     starfish
    0.45
    Activations Density 0.008%

    No Known Activations