© 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. 18491
    Prev
    Next
    INDEX
    Explanations

    security and financial dealings

    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
    3
    0.38
     this
    0.36
    4
    0.34
    9
    0.32
    2
    0.32
    8
    0.32
    -
    0.31
    Local
    0.31
     these
    0.30
    1
    0.30
    POSITIVE LOGITS
     maaaring
    0.39
     আকারের
    0.38
     curviliné
    0.37
     maneiras
    0.36
    impulan
    0.36
     analges
    0.35
     insuffis
    0.35
    摖
    0.34
     physician
    0.34
    েমনি
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.