© 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. 26173
    Prev
    Next
    INDEX
    Explanations

    diverse languages in academic texts

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

    product value scaling civilization

    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
    比如說
    0.47
    ⽇
    0.45
    ⾼
    0.44
    Frag
    0.42
     తొలి
    0.42
    从而
    0.41
     acond
    0.40
     alerg
    0.40
    फाइनल
    0.40
    loading
    0.39
    POSITIVE LOGITS
     Erfahrungen
    0.48
     규칙
    0.48
    Κ
    0.47
     Erinner
    0.46
    ksz
    0.46
    RSSI
    0.46
     ს
    0.46
     intelligents
    0.45
    alnız
    0.45
     コート
    0.45
    Activations Density 0.000%

    No Known Activations