© 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. 131342
    Prev
    Next
    INDEX
    Explanations

    purpose behind

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

    building something new

    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
     rhymes
    0.52
    ్రియ
    0.49
    の世界
    0.48
    Ꮯ
    0.48
     REALLY
    0.47
    ى
    0.45
     रिया
    0.45
    ை
    0.45
     Держа
    0.44
    это
    0.44
    POSITIVE LOGITS
    vel
    0.46
    dracht
    0.45
    phantom
    0.45
    dsc
    0.45
    pet
    0.44
     vel
    0.43
     പ്രത്യേക
    0.43
    urangan
    0.42
     bào
    0.42
    anav
    0.42
    Activations Density 0.001%

    No Known Activations