© 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. 120897
    Prev
    Next
    INDEX
    Explanations

    parent child survivors many

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

    API key claim

    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
    மன்
    0.56
     Percolation
    0.55
    ட்டை
    0.51
    蹂
    0.49
     vardı
    0.47
     स्पोर्ट
    0.47
    らなかった
    0.47
    して
    0.47
    ِی
    0.47
    मण
    0.47
    POSITIVE LOGITS
    ét
    0.43
    éth
    0.42
     입장
    0.42
     appliance
    0.41
    zys
    0.41
    ed
    0.41
    退
    0.41
    doch
    0.40
     AFFAIRS
    0.40
    잠
    0.40
    Activations Density 0.000%

    No Known Activations