© 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. 174280
    Prev
    Next
    INDEX
    Explanations

    velcro, signed, chapter, letter, grams

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

    end of sentence structure

    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
     схема
    0.53
     planilha
    0.51
     মনোনয়নপত্র
    0.46
    ৬৮
    0.46
     expediente
    0.45
     STORM
    0.45
     комбина
    0.45
    👭
    0.44
     huevo
    0.44
    岧
    0.44
    POSITIVE LOGITS
     de
    0.53
    ES
    0.50
     infused
    0.46
    ).
    0.44
     affirms
    0.43
    (),
    0.42
    riqu
    0.42
    thr
    0.42
    ers
    0.42
    es
    0.41
    Activations Density 0.000%

    No Known Activations