© 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. 45417
    Prev
    Next
    INDEX
    Explanations

    aforementioned described

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

    aforementioned, said, above-mentioned

    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
    Enc
    0.46
    Pass
    0.45
    Agen
    0.44
    While
    0.43
    A
    0.43
    Besides
    0.42
    The
    0.42
    Uh
    0.42
    Commonwealth
    0.41
    ▭
    0.41
    POSITIVE LOGITS
     उक्त
    0.47
    itiert
    0.46
     aforementioned
    0.44
    ctrine
    0.43
     dechlorination
    0.42
    ↵↵↵
    0.41
    described
    0.41
     זו
    0.41
     考え
    0.40
    ータル
    0.40
    Activations Density 0.000%

    No Known Activations