© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131485
    Prev
    Next
    INDEX
    Explanations

    foreign words like eine,aksud

    np_acts-logits-general · gemini-2.5-flash-lite

    defining situations or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIS
    0.46
    꼬
    0.46
     প্রবৃত্ত
    0.46
    }(\
    0.45
    EK
    0.43
     Sprinkle
    0.42
     koriste
    0.41
    스코
    0.41
    정에
    0.41
    식을
    0.40
    POSITIVE LOGITS
    eine
    0.53
     Faun
    0.47
     maksud
    0.45
    khidmat
    0.44
     acidified
    0.44
    tiket
    0.44
    laublich
    0.44
    翀
    0.44
     flammable
    0.43
     sebuah
    0.43
    Activations Density 0.001%

    No Known Activations