© 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. 212717
    Prev
    Next
    INDEX
    Explanations

    Lelaina, Layla, Leela, Lelli, Leitão

    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
     ex
    0.45
     source
    0.43
     diber
    0.42
     pronto
    0.41
     lager
    0.41
     multiverse
    0.41
     percentage
    0.41
    ᔨ
    0.41
     varm
    0.40
     nonlocal
    0.40
    POSITIVE LOGITS
    achtung
    0.39
    Zoom
    0.36
    Opening
    0.36
    heath
    0.35
    Stand
    0.34
     оте
    0.34
    Buzz
    0.34
    スタンド
    0.34
    Events
    0.34
     FIG
    0.34
    Activations Density 0.002%

    No Known Activations