© 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. 102206
    Prev
    Next
    INDEX
    Explanations

    root, green, rock

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

    embedded computers

    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
     does
    0.46
    са
    0.44
    im
    0.44
    а
    0.44
    idas
    0.43
    mila
    0.43
    г
    0.42
    NFT
    0.42
    冪
    0.41
    rotating
    0.41
    POSITIVE LOGITS
    론
    0.52
     خبرگزاری
    0.49
     حسین
    0.49
     האח
    0.47
     kttt
    0.47
     حكوم
    0.46
     частей
    0.45
     pemerintah
    0.45
     Atti
    0.44
     anisotrop
    0.44
    Activations Density 0.001%

    No Known Activations