© 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. 142997
    Prev
    Next
    INDEX
    Explanations

    Daily Method Management

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

    somewhat awkward

    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
    FUENTE
    0.51
    मॉ
    0.49
    邁
    0.48
    Maintaining
    0.46
    strahlung
    0.46
    Schwarz
    0.46
    ┈┈
    0.44
    འ
    0.43
    ــــــــ
    0.42
    ས
    0.42
    POSITIVE LOGITS
     orchids
    0.55
    ih
    0.50
    )(=
    0.50
     FAIR
    0.50
     Ordnance
    0.49
     lures
    0.49
     deodorant
    0.47
     Yachts
    0.47
     orator
    0.47
    ik
    0.46
    Activations Density 0.000%

    No Known Activations