© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 165729
    Prev
    Next
    INDEX
    Explanations

    Find complete details about

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

    recognizing prepositional phrases

    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
    ॉजी
    0.50
     quantile
    0.49
     आँ
    0.49
    팩
    0.48
     төр
    0.46
    crossentropy
    0.46
    menuid
    0.45
     супер
    0.45
     कर्फ्यू
    0.45
    qty
    0.44
    POSITIVE LOGITS
    مت
    0.54
    California
    0.53
    <!
    0.53
    Those
    0.52
    It
    0.49
    دود
    0.47
    If
    0.47
    Nicht
    0.47
    يل
    0.46
     almeno
    0.46
    Activations Density 0.001%

    No Known Activations