© 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. 26269
    Prev
    Next
    INDEX
    Explanations

    support the

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

    returns the index

    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
    li
    0.53
    itt
    0.51
    ities
    0.49
    ity
    0.48
    闥
    0.47
    能力
    0.45
    ytics
    0.45
    bats
    0.44
    ul
    0.44
    glichkeiten
    0.44
    POSITIVE LOGITS
     poprzed
    0.47
     రచ
    0.46
     unw
    0.45
     febru
    0.43
     tink
    0.43
     தெரி
    0.42
     écriv
    0.42
     információ
    0.42
    쓴
    0.42
     ungew
    0.41
    Activations Density 0.000%

    No Known Activations