© 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. 157865
    Prev
    Next
    INDEX
    Explanations

    discourse depression accompaniment sampling conference

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

    concrete experience

    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
    tbLabel
    0.46
     invariably
    0.46
    Permission
    0.43
    τί
    0.43
    permission
    0.43
    እ
    0.43
    StudentRecord
    0.42
    σαν
    0.41
     Permission
    0.41
    <0x1E>
    0.41
    POSITIVE LOGITS
     deklar
    0.50
    teki
    0.47
     mip
    0.45
     probl
    0.44
     fotografi
    0.44
     trafik
    0.44
     komputer
    0.43
     जीने
    0.43
     giochi
    0.43
     minimo
    0.43
    Activations Density 0.000%

    No Known Activations