© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19192
    Prev
    Next
    INDEX
    Explanations

    bold formatting or specific separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     généralement
    0.49
    ຜະລິດຕະພັນ
    0.48
     ఉపయోగ
    0.48
     aproximadamente
    0.48
    ケーション
    0.48
     क्वेश्चंस
    0.46
    供应
    0.46
    客
    0.44
     поня
    0.44
     наиболее
    0.43
    POSITIVE LOGITS
    abhut
    0.55
    ru
    0.47
    lu
    0.45
    avacanam
    0.45
    HU
    0.45
    نر
    0.44
    ra
    0.43
     夕
    0.43
    Decre
    0.43
    cu
    0.42
    Activations Density 0.005%

    No Known Activations