© 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. 243627
    Prev
    Next
    INDEX
    Explanations

    self worth

    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
     readout
    0.46
     Toch
    0.45
     jeweils
    0.42
    小
    0.41
    虽然
    0.39
    بعض
    0.39
    Chú
    0.38
    ราย
    0.38
     ಉಪ
    0.38
    Polynomial
    0.38
    POSITIVE LOGITS
     सुकून
    0.47
    anglement
    0.46
     pake
    0.45
     Бон
    0.45
    quatre
    0.44
     கட்டமை
    0.44
    мол
    0.43
     лежит
    0.43
     banjir
    0.43
    ⛏
    0.43
    Activations Density 0.001%

    No Known Activations