© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 208627
    Prev
    Next
    INDEX
    Explanations

    interpersonal phrases

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

    Factorial calculations and funerals

    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
     to
    0.49
     shortened
    0.49
    缩
    0.48
     D
    0.46
     temp
    0.46
     Mind
    0.46
     Elvis
    0.45
    专
    0.45
     Laud
    0.44
     brag
    0.44
    POSITIVE LOGITS
     разви
    0.51
    endorong
    0.51
     मिरची
    0.51
    entretien
    0.50
     эпизо
    0.50
     раствора
    0.50
     районов
    0.49
    estrian
    0.49
    ocity
    0.48
     जवळपास
    0.47
    Activations Density 0.000%

    No Known Activations