© 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. 27603
    Prev
    Next
    INDEX
    Explanations

    argued that

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

    suggesting, keep, powerful, watching, Jackson

    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
     لوبې
    0.53
     اکاؤنٹ
    0.51
     Disabilities
    0.50
     उत्पीड़न
    0.50
    ğan
    0.48
    鏨
    0.48
     دہ
    0.48
    ńcz
    0.47
    łach
    0.47
    颐
    0.46
    POSITIVE LOGITS
    Compact
    0.46
    িসি
    0.41
    اسية
    0.41
    opolymer
    0.41
    キーワード
    0.41
    union
    0.40
    κο
    0.40
    ongoose
    0.40
    унд
    0.40
     compact
    0.40
    Activations Density 0.000%

    No Known Activations