© 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. 134001
    Prev
    Next
    INDEX
    Explanations

    historical and factual markers

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

    leading to deviations

    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
    m
    0.42
    have
    0.40
    nd
    0.40
    covid
    0.40
    c
    0.40
    eny
    0.39
    d
    0.39
     there
    0.38
    f
    0.38
    there
    0.38
    POSITIVE LOGITS
    かもしれませんが
    0.52
    しましたが
    0.49
    ™,
    0.46
    していますが
    0.46
    いましたが
    0.45
    いますが
    0.45
     pokuš
    0.45
     ngunit
    0.45
    ₂,
    0.44
     자신의
    0.44
    Activations Density 0.002%

    No Known Activations