© 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. 25357
    Prev
    Next
    INDEX
    Explanations

    practicalities conditions pricing

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

    2

    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
    ->
    0.46
    ans
    0.46
    ]:
    0.42
     Considered
    0.42
     Determining
    0.42
    rect
    0.41
     ans
    0.41
     Assessing
    0.40
    vector
    0.39
     Consider
    0.39
    POSITIVE LOGITS
     성장
    0.43
    钀
    0.42
     fréquemment
    0.41
    ቃት
    0.40
     informacija
    0.40
     조건을
    0.40
    ስተ
    0.39
     connectedness
    0.38
     культура
    0.38
     vibrancy
    0.37
    Activations Density 0.000%

    No Known Activations