© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13865
    Prev
    Next
    INDEX
    Explanations

    units converted

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

    mathematical operations and conversions

    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_16k_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
    供应
    0.41
    푎
    0.40
     дори
    0.40
     жаса
    0.39
    UNIVERS
    0.39
    ISSU
    0.38
     supple
    0.38
     यज्ञ
    0.38
    嗘
    0.38
     फ्ले
    0.38
    POSITIVE LOGITS
     terminating
    0.46
     expressed
    0.44
     }>;
    0.43
    rufen
    0.42
     terminated
    0.41
    িদের
    0.40
     terminates
    0.39
     SMTP
    0.39
     raining
    0.39
     ভয়ঙ্কর
    0.39
    Activations Density 0.011%

    No Known Activations