© 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. 78919
    Prev
    Next
    INDEX
    Explanations

    t the

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

    akin to Plakinastrella

    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
    )，
    0.43
    foreign
    0.42
     якобы
    0.40
    Essentially
    0.40
     ڕۆ
    0.40
    ossi
    0.38
    hul
    0.38
    果
    0.38
    another
    0.38
    要知道
    0.38
    POSITIVE LOGITS
     multitasking
    0.52
    dcsset
    0.48
     sgt
    0.47
     बीएसटीसी
    0.47
     CRF
    0.46
     ANS
    0.46
     tweaking
    0.46
     emoz
    0.45
     తగ్గ
    0.45
     multidiscipl
    0.45
    Activations Density 0.000%

    No Known Activations