© 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. 61553
    Prev
    Next
    INDEX
    Explanations

    preparing for adulthood

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

    how clouds form

    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
     Agriculture
    0.49
    朐
    0.46
     bedrooms
    0.45
     époque
    0.44
     trifling
    0.43
    হাস
    0.43
    बाजी
    0.42
    ᴱ
    0.42
    ırı
    0.42
     AGRICULTURE
    0.41
    POSITIVE LOGITS
    nelly
    0.51
    ayo
    0.51
    Settings
    0.50
     στις
    0.50
    aya
    0.50
    questao
    0.49
    ｎ
    0.49
    ato
    0.48
     повече
    0.48
    Agu
    0.48
    Activations Density 0.000%

    No Known Activations