© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192492
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_40_width_262k_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
    δα
    0.46
    Touching
    0.40
    IRD
    0.39
    IRO
    0.38
    ანს
    0.37
    aco
    0.36
    Ben
    0.36
    E
    0.36
     mor
    0.34
    =+
    0.34
    POSITIVE LOGITS
     nineteen
    0.63
     नाइन
    0.59
     nine
    0.59
     ৪৯
    0.59
     ۹
    0.55
     ninety
    0.54
     nueve
    0.54
     девя
    0.54
    ９
    0.54
     ৯
    0.52
    Activations Density 0.052%

    No Known Activations