© 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. 59671
    Prev
    Next
    INDEX
    Explanations

    concepts after 'a', 'the', 'flow', 'book', 'limits'

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

    concepts and diversity

    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
    ボリューム
    0.47
     WERE
    0.42
     వెంటనే
    0.42
    Judging
    0.42
    很大的
    0.41
    㢄
    0.41
    藁
    0.41
    小的
    0.40
    難
    0.40
    児童
    0.40
    POSITIVE LOGITS
     spesies
    0.53
     ubiquitous
    0.51
    منابع
    0.46
     espécies
    0.46
     seu
    0.44
     śmier
    0.43
     melalui
    0.43
     mondiale
    0.43
     fontes
    0.43
     mekanisme
    0.43
    Activations Density 0.000%

    No Known Activations