© 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. 253269
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ্রেট
    0.58
     nöt
    0.55
    on
    0.54
    ート
    0.50
    id
    0.49
    ilane
    0.47
    𝙞
    0.47
    ત્મ
    0.47
    వ్
    0.46
    íg
    0.46
    POSITIVE LOGITS
    ể
    0.47
     numerosi
    0.46
     berdiri
    0.45
     ,'
    0.44
     kater
    0.44
     capt
    0.44
    captivity
    0.44
    Capt
    0.43
    alah
    0.41
     enlarg
    0.41
    Activations Density 0.002%

    No Known Activations