© 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. 19989
    Prev
    Next
    INDEX
    Explanations

    making it or them

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

    making it suitable

    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
    ので
    0.47
    4
    0.46
     वैसा
    0.45
     chia
    0.45
     ώστε
    0.44
    q
    0.44
    キュ
    0.44
    ワ
    0.43
     ހ
    0.43
     Laugh
    0.42
    POSITIVE LOGITS
    这也是
    0.60
     this
    0.53
    ünschen
    0.52
    Это
    0.50
     questo
    0.50
    它是
    0.48
    órios
    0.47
    это
    0.47
    ائنات
    0.47
    inais
    0.47
    Activations Density 0.025%

    No Known Activations