© 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. 243963
    Prev
    Next
    INDEX
    Explanations

    dumpster size

    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
     outpatient
    0.49
     isometry
    0.47
     anisotropy
    0.46
    ه
    0.45
    🫡
    0.45
     amacı
    0.45
     detachment
    0.45
     accompaniment
    0.45
     oxidant
    0.44
     اسٹ
    0.44
    POSITIVE LOGITS
     ነው።
    0.45
    悽
    0.44
     vég
    0.43
    }.
    0.42
    вето
    0.41
     DLL
    0.40
    date
    0.40
     Whitley
    0.40
     цело
    0.39
     vra
    0.39
    Activations Density 0.001%

    No Known Activations