© 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. 122076
    Prev
    Next
    INDEX
    Explanations

    opening the, needed for, refund the

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

    fine-tuning for specific tasks

    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
     मार्ग
    0.44
    锁
    0.44
    lipstick
    0.43
    颁
    0.43
    她们
    0.41
    Tarjeta
    0.41
    文件夹
    0.41
    程式
    0.41
     بولی
    0.40
     हरित
    0.40
    POSITIVE LOGITS
    zocht
    0.51
    țe
    0.48
    tsi
    0.44
    ضی
    0.42
    hension
    0.41
     recharging
    0.40
    parat
    0.39
    す
    0.39
    REQ
    0.38
    ctive
    0.38
    Activations Density 0.000%

    No Known Activations