© 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. 17064
    Prev
    Next
    INDEX
    Explanations

    words like Barite, Blue, infarction

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

    recruiting, arch, steering, Scissors

    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
    ז
    0.54
    ཋ
    0.50
    Daten
    0.49
    ח
    0.49
    לת
    0.48
    antwort
    0.47
    ८
    0.47
    राजनी
    0.46
    데이터
    0.46
    ט
    0.46
    POSITIVE LOGITS
     l
    0.56
     and
    0.51
     you
    0.48
     Camera
    0.47
     the
    0.47
     d
    0.47
     School
    0.46
     ‘
    0.45
     all
    0.45
     m
    0.45
    Activations Density 0.330%

    No Known Activations