© 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. 153707
    Prev
    Next
    INDEX
    Explanations

    own solar

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

    country-by-country breakdownlikely shortimmediate existentialAmazon Associates

    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
    তীর্থ
    0.49
    рі
    0.45
    বিশ্ব
    0.42
     SITE
    0.42
    ။
    0.41
     తేదీ
    0.41
     Loeb
    0.41
     RANGE
    0.40
     Caleb
    0.40
    NSNumber
    0.40
    POSITIVE LOGITS
     ගැ
    0.47
    camp
    0.46
    arakatuh
    0.42
     mishaps
    0.41
     compartments
    0.41
     stumbled
    0.40
     드러
    0.40
     꾸
    0.39
    )//
    0.39
     pragmatic
    0.39
    Activations Density 0.001%

    No Known Activations