© 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. 34427
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    high pressure or entrance blocked

    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
     sewer
    0.46
     seabed
    0.45
    3
    0.45
     continuum
    0.44
     unfore
    0.44
     wetlands
    0.43
     rebuttal
    0.43
     study
    0.43
     MRS
    0.43
    7
    0.43
    POSITIVE LOGITS
    உலக
    0.47
    观众
    0.44
    Saldo
    0.43
     Informationen
    0.42
    שים
    0.41
    Neue
    0.40
    婚礼
    0.40
    úde
    0.39
    รายละเอียด
    0.39
    ﭥ
    0.39
    Activations Density 0.000%

    No Known Activations