© 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. 189338
    Prev
    Next
    INDEX
    Explanations

    another layer

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

    contrast and continuation

    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
     hardness
    0.41
     c
    0.41
     «
    0.40
     ebben
    0.40
     énorm
    0.40
     AT
    0.40
    在中
    0.39
    0.39
     lateral
    0.39
     Lateral
    0.39
    POSITIVE LOGITS
    ６
    0.54
    dagger
    0.49
    س
    0.49
    栩
    0.48
    娑
    0.48
    酒
    0.48
    狎
    0.48
    猖
    0.47
    ποίηση
    0.47
    瞧
    0.46
    Activations Density 0.000%

    No Known Activations