© 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. 208527
    Prev
    Next
    INDEX
    Explanations

    fairy tale

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

    relays via

    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
    कार्बन
    0.51
    ட்டை
    0.48
     tổn
    0.48
     enzim
    0.47
    ጡ
    0.47
     vittime
    0.46
    contraction
    0.46
    लिन
    0.46
     یورپی
    0.46
    相位
    0.45
    POSITIVE LOGITS
    ]
    0.44
     ചെയ്യാ
    0.44
     スカート
    0.43
     Roanoke
    0.43
     Claremont
    0.42
     أيام
    0.42
     Roper
    0.42
     Valley
    0.42
    ť
    0.42
    harth
    0.41
    Activations Density 0.000%

    No Known Activations