© 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. 40-GEMMASCOPE-2-RES-65K
    7. 49990
    Prev
    Next
    INDEX
    Explanations

    along the water

    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_40_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
    橦
    0.43
     ঢে
    0.40
    apod
    0.37
     va
    0.36
     Johnston
    0.36
     Romano
    0.36
     segment
    0.35
    తా
    0.35
    ￠
    0.35
    tero
    0.35
    POSITIVE LOGITS
     riverside
    1.67
     lakeside
    1.45
     waterfront
    1.34
    ริม
    1.29
     вдоль
    1.16
    沿
    1.13
     river
    1.09
     seaside
    1.09
     Waterfront
    1.08
     entlang
    0.97
    Activations Density 0.082%

    No Known Activations