© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45369
    Prev
    Next
    INDEX
    Explanations

    probing user intent or AI function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ｴ
    0.48
    已經
    0.45
    ,_
    0.45
    已经
    0.44
    NO
    0.43
    了承
    0.43
    ances
    0.42
    А
    0.42
    梩
    0.41
    arked
    0.41
    POSITIVE LOGITS
     creatures
    0.51
     dobbiamo
    0.50
     metadata
    0.49
     behaviors
    0.48
     storytelling
    0.46
     ideology
    0.45
     semantic
    0.45
     backlog
    0.45
     scalable
    0.45
     neutrophils
    0.45
    Activations Density 0.008%

    No Known Activations