© 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. 228605
    Prev
    Next
    INDEX
    Explanations

    twice per day

    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
    i
    0.63
     is
    0.52
    w
    0.51
    s
    0.51
    l
    0.51
    Vers
    0.50
    sip
    0.50
    ி
    0.49
    ي
    0.48
    PS
    0.47
    POSITIVE LOGITS
     birdseye
    0.54
     ঠে
    0.52
     刺繍
    0.49
     کمپنیوں
    0.49
    ലോ
    0.47
     می‌توانید
    0.47
    𒉋
    0.47
    府県
    0.46
     compds
    0.46
     orchards
    0.45
    Activations Density 0.000%

    No Known Activations