© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75988
    Prev
    Next
    INDEX
    Explanations

    potential costs and partnership

    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_262k_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
    ᔪ
    0.45
     М
    0.44
    オ
    0.43
    単位
    0.42
    ०
    0.41
    Illinois
    0.40
    О
    0.40
     П
    0.39
    İK
    0.39
    单位
    0.38
    POSITIVE LOGITS
    carts
    0.41
     entdecken
    0.40
    rukt
    0.38
     gull
    0.38
     méthodes
    0.38
    perty
    0.37
    يمة
    0.37
     konfigur
    0.36
    amiseks
    0.36
    alus
    0.36
    Activations Density 0.001%

    No Known Activations