© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 100112
    Prev
    Next
    INDEX
    Explanations

    smell of brine

    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_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
    Colour
    0.41
    sz
    0.40
     Farbe
    0.40
    Qb
    0.40
    Shuffle
    0.38
    Proguard
    0.38
    姥
    0.38
    ugly
    0.38
    Floating
    0.37
    Fert
    0.37
    POSITIVE LOGITS
    煐
    0.39
     programma
    0.38
    ज़ा
    0.38
     oraș
    0.38
     genere
    0.38
     Desert
    0.36
     secretariat
    0.36
     seriously
    0.35
     programa
    0.35
     appreciable
    0.35
    Activations Density 0.000%

    No Known Activations