© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 60
    Prev
    Next
    INDEX
    Explanations

    numbers or statistics

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

    ISO numbers

    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_53_width_65k_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
     九
    0.77
     २४
    0.76
     ২৪
    0.73
    九
    0.73
     девя
    0.70
     १८४
    0.68
     Nine
    0.67
     ৩৪
    0.67
     nueve
    0.66
     nine
    0.65
    POSITIVE LOGITS
    7
    0.46
    😎
    0.43
     सेवन
    0.41
     moderator
    0.35
    </strong>
    0.34
     Moderator
    0.34
     incomparable
    0.33
     கை
    0.32
    ..!
    0.32
    quinolin
    0.31
    Activations Density 0.713%

    No Known Activations