© 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. 138608
    Prev
    Next
    INDEX
    Explanations

    internet service provider (ISP)

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

    factors leading to states

    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
    StartsWith
    0.52
    Lime
    0.52
    Rip
    0.49
    сі
    0.48
     Архів
    0.48
     ৃ
    0.47
     имен
    0.47
    НІ
    0.47
    Rud
    0.47
    Clientes
    0.46
    POSITIVE LOGITS
     sired
    0.49
     compelled
    0.46
    ,
    0.45
     mounting
    0.45
     converged
    0.44
     situated
    0.44
     seventy
    0.43
     snout
    0.43
     huge
    0.43
     yielded
    0.42
    Activations Density 0.000%

    No Known Activations