© 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. 135656
    Prev
    Next
    INDEX
    Explanations

    found information

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

    stories, evaluation, specific topics

    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
    rospective
    0.48
     aides
    0.46
     студент
    0.46
    국
    0.46
     cancellations
    0.45
    })$,
    0.45
    人文
    0.44
     nationalism
    0.44
     synergies
    0.44
     OTS
    0.44
    POSITIVE LOGITS
     沒有
    0.50
     K
    0.45
     Commerce
    0.44
     الرياض
    0.44
     प्रतिष्ठ
    0.44
    setPreferred
    0.44
    adays
    0.43
     Plast
    0.43
     .=
    0.43
     Carp
    0.43
    Activations Density 0.001%

    No Known Activations