© 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. 220198
    Prev
    Next
    INDEX
    Explanations

    needed a dumpster

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

    technical terms and actions

    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
    _{+}$
    0.46
    _"
    0.44
    いますが
    0.43
    -}\
    0.43
    न्त्री
    0.42
    \_
    0.42
    ঞ্চলের
    0.42
     источников
    0.41
    阻止
    0.41
     परिजनों
    0.41
    POSITIVE LOGITS
     gak
    0.48
    อม
    0.48
    槓
    0.47
     ©
    0.46
     (†
    0.46
    GAIN
    0.46
    ⸙
    0.46
     karma
    0.45
     zobac
    0.45
     nir
    0.45
    Activations Density 0.001%

    No Known Activations