© 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. 64395
    Prev
    Next
    INDEX
    Explanations

    provincial assembly minister

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

    holographic cyberpunk aesthetic

    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
     کہاں
    0.51
    มิ
    0.50
    सुबह
    0.49
     می
    0.48
     ')
    0.46
     நேற்று
    0.46
     நினைவு
    0.45
     \%)$,
    0.45
     eſ
    0.45
     undangan
    0.45
    POSITIVE LOGITS
     Minister
    0.45
    Minister
    0.45
    AMES
    0.44
    TOK
    0.42
     Attorney
    0.42
    ad
    0.42
     Ramon
    0.42
     শ্রীযুক্ত
    0.42
    <0x9C>
    0.41
     A
    0.41
    Activations Density 0.000%

    No Known Activations