© 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. 77253
    Prev
    Next
    INDEX
    Explanations

    art featuring

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

    That translates to

    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
    ub
    0.52
    Prefab
    0.48
    ü
    0.48
    warts
    0.47
    ación
    0.47
     Reasoning
    0.47
     पर
    0.46
    Cons
    0.46
    âm
    0.46
    opathic
    0.46
    POSITIVE LOGITS
     Gemeinden
    0.45
     گلوکار
    0.44
     شاهد
    0.43
    ேன்
    0.43
     گوئی
    0.43
    <unused82>
    0.42
     المعروف
    0.42
     comenzaron
    0.42
    弹性
    0.41
    多数
    0.41
    Activations Density 0.000%

    No Known Activations