© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 26
    Prev
    Next
    INDEX
    Explanations

    Differential Dynamic Microscopy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     reckons
    2.18
     with
    2.16
    '
    2.10
    ’
    2.08
     explains
    1.98
     is
    1.93
     predicts
    1.86
    Im
    1.86
    inerary
    1.86
     was
    1.85
    POSITIVE LOGITS
     fizik
    3.02
    tableFuture
    2.84
    끽
    2.67
     afar
    2.65
    liš
    2.59
     zač
    2.48
    нутри
    2.46
    תוך
    2.45
     inanimate
    2.44
    rizable
    2.42
    Activations Density 0.270%

    No Known Activations