© 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-262K
    7. 194675
    Prev
    Next
    INDEX
    Explanations

    where the

    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_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
     complained
    0.44
     retainer
    0.40
     complain
    0.39
    icità
    0.39
     reimbursed
    0.39
     බෙ
    0.38
     productId
    0.38
     갖
    0.38
    atown
    0.38
    nesota
    0.37
    POSITIVE LOGITS
    留意
    0.39
    AndroidManifest
    0.38
    zuführen
    0.37
     voegen
    0.35
    chu
    0.35
    ект
    0.35
    tom
    0.34
     subsets
    0.34
     danske
    0.34
    permutation
    0.34
    Activations Density 0.000%

    No Known Activations