© 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. 37175
    Prev
    Next
    INDEX
    Explanations

    version numbers

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

    version numbers like 0.0.1

    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
    ピ
    0.40
    リー
    0.40
     tomb
    0.38
    ڵ
    0.38
    గ
    0.38
    می
    0.38
    월
    0.38
    エ
    0.38
    ण्डी
    0.37
    오
    0.36
    POSITIVE LOGITS
    之时
    0.47
     けれど
    0.47
    させて頂
    0.46
     सेवन
    0.45
     একান্ত
    0.45
    ត្រូវការ
    0.45
    ravenous
    0.44
    代謝
    0.44
    étel
    0.43
    ക്ഷണ
    0.43
    Activations Density 0.002%

    No Known Activations