© 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. 149735
    Prev
    Next
    INDEX
    Explanations

    salt-free

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

    detecting signals before or after

    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
    ట్స్
    0.51
     VIR
    0.47
     autof
    0.46
    ifilm
    0.44
    可以直接
    0.44
    (',',$
    0.43
     Directly
    0.42
     INCREASE
    0.42
     fat
    0.42
    hotmail
    0.40
    POSITIVE LOGITS
    当社
    0.50
    عود
    0.45
    переди
    0.44
     বিপদ
    0.44
     этого
    0.44
    That
    0.43
    UM
    0.43
    W
    0.43
    ໃນ
    0.42
    _
    0.42
    Activations Density 0.001%

    No Known Activations