© 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. 64443
    Prev
    Next
    INDEX
    Explanations

    limiting single something fish suit

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

    Roth IRA

    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
     ቁ
    0.48
    anglement
    0.47
    들아
    0.46
     осна
    0.45
     дослі
    0.45
    transl
    0.44
     масштаб
    0.44
     дослід
    0.44
     ինչ
    0.44
    ծ
    0.43
    POSITIVE LOGITS
    ى
    0.66
     Sick
    0.55
     Ammo
    0.55
     Naf
    0.54
     Branco
    0.53
     Mah
    0.52
     customers
    0.52
     Jedi
    0.51
     Creo
    0.49
    WAT
    0.49
    Activations Density 0.000%

    No Known Activations