© 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. 229329
    Prev
    Next
    INDEX
    Explanations

    dog food; Teaching With Technology; creditors know; Having ordered

    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
    П
    0.46
     ಸಾ
    0.45
     कपिल
    0.45
     λοι
    0.45
    omir
    0.44
     अद
    0.44
     নয়
    0.43
    orka
    0.42
     સ્વા
    0.42
     ସ
    0.42
    POSITIVE LOGITS
    warl
    0.49
    Firstly
    0.49
     amts
    0.49
     الكسور
    0.49
     provincias
    0.48
    砺
    0.48
    Stainless
    0.48
     sphinct
    0.48
     configuración
    0.47
    防护
    0.47
    Activations Density 0.000%

    No Known Activations