© 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. 182255
    Prev
    Next
    INDEX
    Explanations

    guarantee or collapse

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

    magnitude

    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
    ])[
    0.45
    炀
    0.45
     carelessly
    0.44
     量
    0.43
     обозна
    0.43
     intelligently
    0.42
     entscheid
    0.42
    젤
    0.42
     stanje
    0.41
     හෝ
    0.41
    POSITIVE LOGITS
    GAMMA
    0.50
    Gamma
    0.49
    Serbia
    0.49
    麴
    0.48
    but
    0.48
    rivate
    0.48
    (".
    0.47
    ου
    0.47
    nte
    0.46
    lukan
    0.46
    Activations Density 0.000%

    No Known Activations