© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105812
    Prev
    Next
    INDEX
    Explanations

    legal and multilingual terms

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

    calculating checksums

    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
     tilt
    0.47
    호
    0.43
     Acad
    0.43
    owment
    0.42
    ходя
    0.42
     tilts
    0.41
     가서
    0.40
     yow
    0.40
    iviato
    0.40
     عظ
    0.40
    POSITIVE LOGITS
    েই
    0.56
    ète
    0.51
    zés
    0.51
     similaire
    0.50
    েন্টে
    0.50
     $\}$
    0.49
     অস্ট্রেল
    0.49
     années
    0.48
     weitere
    0.47
     pretože
    0.47
    Activations Density 0.001%

    No Known Activations