© 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. 169419
    Prev
    Next
    INDEX
    Explanations

    specific words after common ones

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

    cases, still not, whales undertake, highly scalable

    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
    ところに
    0.46
    安い
    0.45
     oscillators
    0.44
    오는
    0.44
    𝑋
    0.43
    :...
    0.43
    ogeneous
    0.43
     oscillating
    0.42
     pia
    0.42
    etok
    0.41
    POSITIVE LOGITS
    coma
    0.46
    umba
    0.44
     vulve
    0.43
    ⁡</
    0.42
    vay
    0.42
    ván
    0.42
     nghịch
    0.42
    Ắ
    0.42
    utta
    0.42
     incluso
    0.41
    Activations Density 0.000%

    No Known Activations