© 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. 165943
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and foreign words

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

    changing standards and rates

    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
    ausea
    0.42
    ákat
    0.42
     ASAP
    0.41
    orn
    0.41
     sooner
    0.40
    is
    0.39
     ό
    0.39
     tills
    0.39
     आ
    0.39
    athermy
    0.39
    POSITIVE LOGITS
     Например
    0.46
     mesela
    0.46
    PCB
    0.46
    XXX
    0.45
     şehir
    0.43
    SMA
    0.43
    Croatian
    0.43
     misalnya
    0.42
    MMA
    0.42
    曌
    0.42
    Activations Density 0.000%

    No Known Activations