© 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. 150935
    Prev
    Next
    INDEX
    Explanations

    God, enough, on

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

    transitional phrases and connectives

    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
    4
    0.50
     –
    0.49
    ümü
    0.49
     смотря
    0.46
    3
    0.45
    5
    0.44
     […]
    0.43
    注重
    0.42
     precisely
    0.41
    dist
    0.41
    POSITIVE LOGITS
     Verh
    0.45
     Rohing
    0.45
    䡓
    0.45
    媺
    0.44
     monomial
    0.44
    ាញ
    0.44
    梘
    0.43
    Puedes
    0.43
     jazy
    0.43
     ఆరోగ్య
    0.43
    Activations Density 0.002%

    No Known Activations