© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5240
    Prev
    Next
    INDEX
    Explanations

    asset, account, Ada Lovelace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    genden
    2.64
     engulfed
    2.64
     elucidate
    2.58
    ל
    2.58
     appellant
    2.42
    र
    2.40
     intentos
    2.37
     alloc
    2.34
    л
    2.32
     आयोजन
    2.31
    POSITIVE LOGITS
     thaliana
    3.70
    sterdam
    3.14
     riscos
    3.01
    িকাংশ
    2.77
    ricult
    2.68
     veces
    2.64
    ENDMENT
    2.59
     bxa
    2.55
     \%$.
    2.51
    तिहासिक
    2.47
    Activations Density 1.413%

    No Known Activations