© 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. 163039
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign languages

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

    costs, doctrine, sole, running, released, interpretation, elaborate, stubborn

    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
    ine
    0.50
    isin
    0.50
     หัว
    0.50
    -
    0.49
     दर्शाता
    0.48
    –
    0.48
    Cre
    0.46
    Парт
    0.46
    Narc
    0.46
    ]
    0.46
    POSITIVE LOGITS
     تقسیم
    0.50
     ہمیں
    0.48
     仕様
    0.48
     حدی
    0.46
    侵害
    0.45
     무엇
    0.44
     کشتی
    0.44
     هزینه
    0.44
    我可以
    0.43
     علمی
    0.43
    Activations Density 0.001%

    No Known Activations