© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    a followed by words

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

    a followed by a word

    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
    9
    0.27
     October
    0.26
    8
    0.25
     ambivalent
    0.24
    7
    0.24
     implementing
    0.23
     November
    0.23
    6
    0.23
     implemented
    0.22
     applying
    0.22
    POSITIVE LOGITS
    н
    0.28
    ד
    0.26
     kişi
    0.24
     multitude
    0.24
     timepiece
    0.23
     veces
    0.23
     prince
    0.21
    к
    0.21
    ie
    0.21
    רי
    0.20
    Activations Density 1.200%

    No Known Activations