© 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. 99115
    Prev
    Next
    INDEX
    Explanations

    legal and business exceptions

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

    gas, Twitter, guarantees, limited

    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
     Abelian
    0.45
     Ambul
    0.42
     ஏற்படுத்து
    0.42
     PARTICULAR
    0.41
     Estudos
    0.41
     React
    0.40
     indulged
    0.40
    烜
    0.40
     Affected
    0.40
     Inhib
    0.39
    POSITIVE LOGITS
     wipe
    0.51
     rubble
    0.49
    ！」
    0.49
     作業
    0.44
    Daniels
    0.44
    !»
    0.43
     truss
    0.43
    𝚘
    0.43
     morale
    0.42
     projectiles
    0.42
    Activations Density 0.000%

    No Known Activations