© 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. 52493
    Prev
    Next
    INDEX
    Explanations

    american terms and religious references

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

    Recursive, mutable, implementation

    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
     তপ
    0.45
     ބ
    0.44
     Peace
    0.44
    agés
    0.44
    ária
    0.43
    larni
    0.43
    пиона
    0.43
    agoza
    0.42
     راجس
    0.42
    ас
    0.42
    POSITIVE LOGITS
    October
    0.47
    思い
    0.47
    american
    0.44
     insert
    0.44
     october
    0.44
    кту
    0.43
    彡
    0.42
    ad
    0.42
     //{
    0.42
    大力
    0.42
    Activations Density 0.000%

    No Known Activations