© 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. 151458
    Prev
    Next
    INDEX
    Explanations

    reducing costs

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

    symbols and punctuation

    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
    ंनो
    0.48
     musste
    0.45
    泻
    0.45
    ņi
    0.45
    
    0.44
    hme
    0.43
    ᐸ
    0.43
     lactate
    0.42
     integer
    0.42
     inse
    0.42
    POSITIVE LOGITS
    Agents
    0.49
    のカ
    0.43
    AW
    0.42
    IX
    0.42
    XI
    0.42
    हित
    0.41
     conformations
    0.41
    Officers
    0.41
     Officers
    0.40
    舎
    0.40
    Activations Density 0.000%

    No Known Activations