© 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. 251825
    Prev
    Next
    INDEX
    Explanations

    thanks or gratitude

    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
    слови
    0.51
     Brésil
    0.49
     FreeBSD
    0.49
    IDO
    0.47
    痱
    0.46
     Niño
    0.46
     Faro
    0.46
     ช่วย
    0.46
     Trời
    0.46
    创始
    0.45
    POSITIVE LOGITS
    ❜
    0.44
    ங்களாக
    0.44
    aken
    0.43
    wald
    0.43
     legions
    0.41
    olar
    0.41
     aggregate
    0.41
    ște
    0.40
    uke
    0.39
    Agg
    0.39
    Activations Density 0.000%

    No Known Activations