© 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. 222358
    Prev
    Next
    INDEX
    Explanations

    steps steps

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

    Driving Impulse Purchases

    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
    Volumes
    0.50
    INSTR
    0.50
    یند
    0.49
    JKLMNOP
    0.49
    RETURNS
    0.49
    ד
    0.48
    INPUT
    0.48
    DISABLE
    0.48
    TYPE
    0.48
    HOME
    0.48
    POSITIVE LOGITS
     ampli
    0.47
     inget
    0.46
     Elys
    0.46
     inti
    0.46
    蠅
    0.45
     連
    0.44
     Council
    0.44
     venues
    0.44
     Quartet
    0.44
    čných
    0.44
    Activations Density 0.001%

    No Known Activations