© 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. 21022
    Prev
    Next
    INDEX
    Explanations

    figures and tables

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

    Section references

    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
    ત્તા
    0.46
     ostatnich
    0.45
    鸴
    0.44
     effectués
    0.42
     copyspace
    0.42
    据悉
    0.42
     tolerancia
    0.42
    খাস্ত
    0.42
    罅
    0.41
    ੱਖ
    0.41
    POSITIVE LOGITS
    6
    0.53
    E
    0.52
    3
    0.51
    5
    0.47
    Ver
    0.46
    4
    0.45
    8
    0.45
    G
    0.43
    end
    0.43
    7
    0.43
    Activations Density 0.019%

    No Known Activations