© 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. 25968
    Prev
    Next
    INDEX
    Explanations

    the way country state world cropland surgery Residency

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

    Understanding the core principles

    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
    }^{*}(
    0.43
    ாய்ச்ச
    0.42
    trex
    0.42
    氀
    0.42
    privileged
    0.41
    田
    0.41
    special
    0.41
    ленно
    0.40
    Ɖ
    0.39
    urón
    0.39
    POSITIVE LOGITS
     කල
    0.49
     কর্মীদের
    0.49
     kaldı
    0.49
     कर्मचारियों
    0.47
     rezerv
    0.46
     നട
    0.46
     নেন
    0.46
     कर्मचारी
    0.45
     පසු
    0.45
     முன்
    0.44
    Activations Density 0.000%

    No Known Activations