© 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. 105098
    Prev
    Next
    INDEX
    Explanations

    stock, dividends, meetings

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

    Personalized prompts

    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
     Friction
    0.45
    bre
    0.44
    Со
    0.43
     &:
    0.42
    álise
    0.42
    ég
    0.41
    ugal
    0.41
     Endocr
    0.41
    ]))
    0.40
    friction
    0.39
    POSITIVE LOGITS
     appris
    0.48
     authorizes
    0.48
     heats
    0.46
     സമ്
    0.46
     samym
    0.46
    ｱ
    0.46
    の大
    0.44
     altid
    0.44
     作業
    0.43
     contest
    0.43
    Activations Density 0.000%

    No Known Activations