© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 166
    Prev
    Next
    INDEX
    Explanations

    summary or dialog

    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
    ahi
    0.21
    rnn
    0.21
    euler
    0.21
    tev
    0.20
    ittances
    0.20
    encils
    0.20
    ᴇ
    0.20
    smallskip
    0.19
    igraf
    0.19
    <unused61>
    0.19
    POSITIVE LOGITS
     WHILE
    0.23
     Hoping
    0.23
     라고
    0.23
     MON
    0.22
     대해서
    0.22
     Description
    0.22
    하면서
    0.22
     এরকম
    0.22
     description
    0.22
    ?(
    0.22
    Activations Density 3.631%

    No Known Activations