© 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. 97078
    Prev
    Next
    INDEX
    Explanations

    possessives and specifics

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

    administrator, physician, shell, kernel, warnings

    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
     koristi
    0.59
    الي
    0.57
    АН
    0.52
     augmenté
    0.52
    thisStudent
    0.51
     ângulo
    0.51
    ਣ
    0.51
     desafíos
    0.50
     lembra
    0.50
     porod
    0.49
    POSITIVE LOGITS
    ‐
    0.47
     interstate
    0.45
     lt
    0.45
     capable
    0.43
    ctr
    0.43
     PTC
    0.43
    钀
    0.43
    Complexity
    0.42
     forest
    0.42
    ict
    0.42
    Activations Density 0.000%

    No Known Activations