© 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. 24416
    Prev
    Next
    INDEX
    Explanations

    masked or redacted information

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

    placeholders for codes and numbers

    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
     olacaktır
    0.53
     insulted
    0.51
    𝚣
    0.51
    abca
    0.50
    ac
    0.49
     yardımcı
    0.49
    дравствуйте
    0.49
     erred
    0.48
    𝚓
    0.48
     amazed
    0.48
    POSITIVE LOGITS
    ोर
    0.47
    ة
    0.47
     الض
    0.47
     الس
    0.46
     స్థ
    0.46
    োপ
    0.45
     LEED
    0.44
    ateau
    0.44
    يل
    0.43
    ש
    0.43
    Activations Density 0.003%

    No Known Activations