© 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. 156295
    Prev
    Next
    INDEX
    Explanations

    object side, saving time, essential to

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

    on the

    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
     ristrutt
    0.57
    خلص
    0.56
     obiettivi
    0.55
     își
    0.54
    庣
    0.52
    rong
    0.52
     asci
    0.51
     deviates
    0.50
     riform
    0.50
     Solaris
    0.49
    POSITIVE LOGITS
    AZ
    0.47
    atro
    0.46
    ä
    0.43
    amburger
    0.42
    ੇ
    0.41
    akes
    0.41
    HA
    0.41
    AH
    0.40
    ager
    0.40
    fox
    0.40
    Activations Density 0.000%

    No Known Activations