© 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. 242711
    Prev
    Next
    INDEX
    Explanations

    statistics and 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
     مقارنه
    0.44
     مقار
    0.44
     결
    0.41
    结
    0.41
    waveform
    0.41
    Comparative
    0.41
    結
    0.39
    ATING
    0.39
    ParamList
    0.39
    と比較
    0.39
    POSITIVE LOGITS
     Copyright
    0.46
     sobri
    0.44
     Adapted
    0.43
     ©
    0.42
    Copyright
    0.42
     dr
    0.41
     salons
    0.41
     *****
    0.40
     barric
    0.39
     estén
    0.39
    Activations Density 0.019%

    No Known Activations