© 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. 175955
    Prev
    Next
    INDEX
    Explanations

    conditional clauses

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

    no privacy, no freedom

    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
     Density
    0.50
    density
    0.47
    correlated
    0.46
    籽
    0.45
    𝐻
    0.45
    mena
    0.44
     आयाम
    0.44
    SAV
    0.44
    密的
    0.44
    軎
    0.43
    POSITIVE LOGITS
     tarn
    0.50
     frantically
    0.50
     riverside
    0.48
     judiciales
    0.48
    isSignedIn
    0.46
     tratando
    0.45
     reunião
    0.44
     colabor
    0.44
     championnat
    0.44
    leftharpoons
    0.44
    Activations Density 0.001%

    No Known Activations