© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51593
    Prev
    Next
    INDEX
    Explanations

    WoW Skins, IT, credible, nevertheless

    np_acts-logits-general · gemini-2.5-flash-lite

    oncology, guitar, plan, asset, merchandise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggen
    0.52
     여기가
    0.49
    ینس
    0.48
     weiteren
    0.46
     mengerjakan
    0.44
    ⴽ
    0.42
    ‌شده
    0.42
     linken
    0.41
    ပိုင်း
    0.40
     जरिए
    0.40
    POSITIVE LOGITS
    レ
    0.48
    ２
    0.48
    PAL
    0.47
    痳
    0.46
    FORE
    0.46
    Ко
    0.43
    ０
    0.43
    আই
    0.42
     குழந்த
    0.42
    দু
    0.42
    Activations Density 0.001%

    No Known Activations