© 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. 181422
    Prev
    Next
    INDEX
    Explanations

    foreign words and affiliations

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

    anticipation of approvals

    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
     válido
    0.55
    ittää
    0.49
     उतनी
    0.43
     válida
    0.43
    ifikasi
    0.42
    锺
    0.41
     Validity
    0.41
    𝒚
    0.41
     தொலை
    0.41
    बलेट
    0.41
    POSITIVE LOGITS
    an
    0.46
     partnership
    0.42
     affiliation
    0.42
    ORUS
    0.42
     సా
    0.42
     quelle
    0.42
    prong
    0.41
     gingen
    0.41
     schwarz
    0.41
     dirigeants
    0.41
    Activations Density 0.001%

    No Known Activations