© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47284
    Prev
    Next
    INDEX
    Explanations

    defines terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Daten
    0.48
    CurrentByte
    0.46
    섀
    0.45
    jogador
    0.45
    अमेर
    0.44
    analisi
    0.43
    संयुक्त
    0.43
    撷
    0.42
    Совет
    0.42
     தோன்ற
    0.42
    POSITIVE LOGITS
    /
    0.61
     faculty
    0.53
     अन्य
    0.51
     weddings
    0.51
     onboarding
    0.51
     cocktails
    0.49
     outfits
    0.49
     façons
    0.47
     (
    0.47
     autres
    0.47
    Activations Density 0.014%

    No Known Activations