© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46283
    Prev
    Next
    INDEX
    Explanations

    explaining how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ils
    0.43
    akkhan
    0.43
    els
    0.42
    ш
    0.40
    aud
    0.39
    igned
    0.39
    Ils
    0.39
    ups
    0.39
    ined
    0.38
    þ
    0.38
    POSITIVE LOGITS
     ryzy
    0.49
     boosts
    0.48
    向けの
    0.47
     mię
    0.46
     opts
    0.46
    クリスマス
    0.45
     italiana
    0.44
     primavera
    0.44
     gana
    0.44
     decides
    0.43
    Activations Density 0.021%

    No Known Activations