© 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. 227467
    Prev
    Next
    INDEX
    Explanations

    directions and involve

    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
    ዷ
    0.48
    esecuzione
    0.45
    ORGE
    0.43
    dW
    0.43
    dS
    0.42
     emblems
    0.42
     এলাম
    0.42
     Hari
    0.41
    Ἥ
    0.41
    ยาง
    0.41
    POSITIVE LOGITS
     envolve
    0.55
    ក្រោម
    0.47
     জড়িয়ে
    0.46
     නම්
    0.45
     naturally
    0.45
     मश
    0.45
     drücken
    0.45
     ફિલ્મ
    0.44
     банков
    0.44
     ක්ර
    0.44
    Activations Density 0.001%

    No Known Activations