© 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. 23673
    Prev
    Next
    INDEX
    Explanations

    German word completions and context

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

    types of abilities

    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
     receives
    0.51
     says
    0.49
     serves
    0.48
     possesses
    0.47
    師
    0.47
     covered
    0.47
     practised
    0.46
     efficiently
    0.46
    や
    0.44
     practices
    0.44
    POSITIVE LOGITS
    ThoughtData
    0.63
     runter
    0.59
    이를
    0.56
    cheiden
    0.53
     pavattati
    0.53
     Bestellung
    0.53
    datei
    0.52
     anderen
    0.52
     Auft
    0.52
    WallArray
    0.52
    Activations Density 0.000%

    No Known Activations