© 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. 172820
    Prev
    Next
    INDEX
    Explanations

    link above or investor

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

    url links

    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
    ش
    0.46
     yon
    0.44
     منف
    0.44
     Additional
    0.44
    你去
    0.44
    다음
    0.42
    midd
    0.41
    你可以
    0.41
    zentration
    0.41
     सर्
    0.40
    POSITIVE LOGITS
    klore
    0.48
    𝟬
    0.47
    anomaly
    0.46
    г
    0.46
    𒈬
    0.45
    сно
    0.45
     ribonucle
    0.44
    носит
    0.44
     生産
    0.43
     ве
    0.43
    Activations Density 0.000%

    No Known Activations