© 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. 78725
    Prev
    Next
    INDEX
    Explanations

    end of service transaction

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

    competitive market, that, when, named

    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
    История
    0.54
    徎
    0.54
    ابی
    0.47
    组
    0.47
    线
    0.47
    িপুর
    0.46
    ㈤
    0.46
    ayani
    0.46
    𝙈
    0.46
    History
    0.46
    POSITIVE LOGITS
     tiempo
    0.54
     lontano
    0.51
     tanto
    0.50
     mama
    0.49
     confianza
    0.49
     आत्मविश्वास
    0.48
     tena
    0.47
     πολλά
    0.47
     fewer
    0.47
     recue
    0.46
    Activations Density 0.000%

    No Known Activations