© 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. 77813
    Prev
    Next
    INDEX
    Explanations

    uppercase and lowercase letters

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

    letters and numbers

    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
     noirâtre
    0.59
    膦
    0.48
    藓
    0.46
     கத
    0.46
    ską
    0.46
    addena
    0.45
    ganggu
    0.45
     परिवेश
    0.44
    mk
    0.44
    铊
    0.44
    POSITIVE LOGITS
     pensioners
    0.61
     pensioner
    0.60
         
    0.55
     pension
    0.49
     recuper
    0.48
     cargo
    0.47
             
    0.47
     and
    0.47
     retiree
    0.46
    धन
    0.46
    Activations Density 0.000%

    No Known Activations