© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48807
    Prev
    Next
    INDEX
    Explanations

    .

    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_40_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
    НИЕ
    0.40
     пона
    0.38
    anil
    0.37
    賞
    0.37
    Arnold
    0.36
    Yap
    0.36
    рё
    0.35
     இல்லாமல்
    0.35
    Ark
    0.35
    共和
    0.35
    POSITIVE LOGITS
     Eminent
    0.40
    ឋ
    0.39
    肃
    0.38
    倩
    0.37
    ത്
    0.37
    dbjc
    0.36
     Hyper
    0.36
     diameters
    0.36
     Statute
    0.36
    ธี
    0.35
    Activations Density 0.000%

    No Known Activations