© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 165042
    Prev
    Next
    INDEX
    Explanations

    Access, Recovery, Custom

    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
    legate
    0.44
     tille
    0.43
    ksa
    0.42
    memor
    0.41
     syukur
    0.41
    noi
    0.41
    肐
    0.41
     గే
    0.39
     keinen
    0.38
    adi
    0.38
    POSITIVE LOGITS
    近づ
    0.41
     MEDIC
    0.38
     MV
    0.38
     vapour
    0.37
    爆炸
    0.36
    MED
    0.36
    MVP
    0.36
    榜
    0.36
    🄴
    0.36
     OCE
    0.35
    Activations Density 0.006%

    No Known Activations