© 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. 154563
    Prev
    Next
    INDEX
    Explanations

    burning time, egg yolk, charge capacity

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

    letters and punctuation followed by words

    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
    CipherText
    0.50
     使っ
    0.50
     parto
    0.47
    zadeh
    0.45
    么
    0.45
     函数
    0.44
     カット
    0.44
     丨
    0.44
    FAN
    0.44
    們
    0.44
    POSITIVE LOGITS
     ngo
    0.49
    लट
    0.49
     ambiguous
    0.42
    भौ
    0.42
    स्थ
    0.42
     Pen
    0.42
    atar
    0.41
     대상
    0.41
     Monte
    0.40
    ियोग
    0.40
    Activations Density 0.000%

    No Known Activations