© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4626
    Prev
    Next
    INDEX
    Explanations

    explain usage types

    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
    7
    1.44
    6
    1.39
     Sensing
    1.39
    8
    1.38
     машин
    1.37
    wachung
    1.33
     senti
    1.30
     Séb
    1.30
     Titanium
    1.30
    Germain
    1.28
    POSITIVE LOGITS
     commentaries
    1.45
    &-
    1.37
     commentator
    1.37
     tutorials
    1.34
     commentators
    1.33
     bowled
    1.28
     columnist
    1.28
     Encyclopaedia
    1.27
    ported
    1.24
    Took
    1.24
    Activations Density 0.000%

    No Known Activations