© 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-16K
    7. 2209
    Prev
    Next
    INDEX
    Explanations

    more than

    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_16k_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
     (
    0.53
     तुम्ही
    0.47
    (
    0.42
    ile
    0.42
    ("
    0.41
    umber
    0.40
     மட்டுமே
    0.40
    '
    0.40
    imeters
    0.39
    itriangular
    0.39
    POSITIVE LOGITS
     γιατί
    0.45
     bởi
    0.40
    鲞
    0.39
     decyz
    0.38
     hebat
    0.38
    ścic
    0.38
     piaci
    0.38
     trži
    0.37
     ERISA
    0.37
    лянчук
    0.37
    Activations Density 0.394%

    No Known Activations