© 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. 168244
    Prev
    Next
    INDEX
    Explanations

    we were

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

    checking trademark availability

    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
    మే
    0.51
     be
    0.49
    អាច
    0.48
    數
    0.48
     सांगतात
    0.46
    வதை
    0.46
    மாறு
    0.46
    𝐩
    0.45
    差異
    0.44
    螻
    0.44
    POSITIVE LOGITS
     dee
    0.45
    nika
    0.44
    スキ
    0.44
     দেখিয়ে
    0.44
    .[
    0.43
    khan
    0.42
    sack
    0.42
    asă
    0.41
    fabs
    0.41
    sym
    0.41
    Activations Density 0.001%

    No Known Activations