© 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. 206464
    Prev
    Next
    INDEX
    Explanations

    presentation or release details

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

    No cream

    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
    atient
    0.49
    InBuffer
    0.48
    ും
    0.45
    டுப
    0.44
    در
    0.44
    ंसिल
    0.44
    துவாக
    0.44
    芓
    0.43
    iciente
    0.42
    Aplic
    0.42
    POSITIVE LOGITS
     пів
    0.46
     Пів
    0.45
     nascita
    0.42
     maroc
    0.41
     зру
    0.41
     econ
    0.40
     liens
    0.40
     calcS
    0.40
     wyk
    0.39
     vaste
    0.39
    Activations Density 0.001%

    No Known Activations