© 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. 49264
    Prev
    Next
    INDEX
    Explanations

    sometimes relay

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

    dating tips

    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
     lakini
    0.44
     Paradis
    0.42
    ary
    0.42
    ⁣⁣
    0.42
    eos
    0.42
    Kentucky
    0.41
    ucci
    0.40
     अभिने
    0.40
     فوری
    0.38
     انتشار
    0.38
    POSITIVE LOGITS
    wür
    0.43
     utilised
    0.41
    َاب
    0.41
    頻道
    0.39
    änn
    0.38
     natür
    0.38
    щення
    0.38
    ائیں
    0.37
    ќ
    0.37
     historically
    0.37
    Activations Density 0.000%

    No Known Activations