© 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. 84886
    Prev
    Next
    INDEX
    Explanations

    formal statements required

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

    applied, ignoring, pin, Impression, objects

    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
     숫
    0.52
    ▔
    0.51
     Kamm
    0.46
     벨
    0.46
    可惜
    0.45
     Акысыз
    0.45
     聞い
    0.45
     椅
    0.44
     kamm
    0.44
     जोड़ी
    0.44
    POSITIVE LOGITS
    άζ
    0.45
     required
    0.44
    зит
    0.44
     that
    0.42
     STUDY
    0.41
     THAT
    0.41
     refreshing
    0.40
     needed
    0.40
     pledges
    0.39
    that
    0.38
    Activations Density 0.001%

    No Known Activations