© 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. 78665
    Prev
    Next
    INDEX
    Explanations

    information or action

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

    loan, television, motel, hostel

    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
    찔
    0.44
     които
    0.44
    newMark
    0.44
     نباش
    0.43
    actifs
    0.42
    ต่างๆ
    0.41
    дев
    0.41
    呲
    0.41
    dup
    0.40
    Ни
    0.40
    POSITIVE LOGITS
     Hostel
    0.49
     an
    0.48
     Television
    0.47
     Dean
    0.46
     Phon
    0.46
     Loan
    0.46
     Audio
    0.45
     verbally
    0.45
     Motel
    0.45
     Location
    0.44
    Activations Density 0.002%

    No Known Activations