© 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. 248501
    Prev
    Next
    INDEX
    Explanations

    9 years, Quick fire

    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
    华人
    0.46
    ୩
    0.46
     reactants
    0.44
    iformis
    0.44
    两
    0.43
    zz
    0.43
    construction
    0.42
     builders
    0.42
    zp
    0.42
    zza
    0.41
    POSITIVE LOGITS
     Chưa
    0.53
     Stimme
    0.53
    თა
    0.50
     Sven
    0.49
     odmah
    0.49
     İşte
    0.49
     മാര്‍
    0.49
     Ừ
    0.48
     Brought
    0.48
    ĐT
    0.48
    Activations Density 0.001%

    No Known Activations