© 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. 237006
    Prev
    Next
    INDEX
    Explanations

    Franklin Covey system

    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
     beiden
    0.44
     klein
    0.44
     demais
    0.44
     quell
    0.43
    !='')
    0.43
    钡
    0.42
     dí
    0.42
    lé
    0.41
     piccolo
    0.41
    _^
    0.41
    POSITIVE LOGITS
     Ung
    0.48
     It
    0.48
     Ass
    0.47
     божомолу
    0.46
    beds
    0.45
     আভ্যন্তরীণ
    0.45
     Actual
    0.44
    abled
    0.43
     실제
    0.43
     priority
    0.43
    Activations Density 0.001%

    No Known Activations