© 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. 33273
    Prev
    Next
    INDEX
    Explanations

    word followed by another word

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

    concepts followed by definite articles

    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
    WINDOWS
    0.48
    прежнему
    0.45
     расте
    0.45
    фото
    0.44
    ኾ
    0.44
    حال
    0.42
    WIDTH
    0.42
     заболе
    0.41
    ТО
    0.41
    ក្រុម
    0.41
    POSITIVE LOGITS
    ur
    0.52
     bhi
    0.46
     नमस्कार
    0.45
     takip
    0.45
     aisa
    0.44
     annuel
    0.44
    ab
    0.43
    enz
    0.43
    ^{*}$.
    0.43
    erde
    0.43
    Activations Density 0.000%

    No Known Activations