© 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. 229018
    Prev
    Next
    INDEX
    Explanations

    category market Croatia Open offer capabilities

    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
    eb
    0.54
     b
    0.53
     veget
    0.53
    ando
    0.52
    egan
    0.52
    ara
    0.51
     CO
    0.51
     WHO
    0.51
     mera
    0.51
     h
    0.50
    POSITIVE LOGITS
    джер
    0.50
    стую
    0.50
    予測
    0.50
    Surprisingly
    0.47
    觎
    0.46
    ૃહ
    0.46
    шений
    0.46
    Xét
    0.46
    ंमध्ये
    0.45
    Didn
    0.45
    Activations Density 0.001%

    No Known Activations