© 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. 30814
    Prev
    Next
    INDEX
    Explanations

    this completely, high standard, let us

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

    focus on benefits and impact

    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
     adjuvant
    0.45
    मित्रा
    0.45
     shells
    0.43
    合物
    0.43
    Professor
    0.41
     protons
    0.41
    у
    0.41
     invertebrates
    0.40
     dysplasia
    0.40
     inhomogeneity
    0.40
    POSITIVE LOGITS
     উপরে
    0.54
    тың
    0.48
     udf
    0.47
    懲
    0.47
    ‌های
    0.45
     Aware
    0.45
    ņas
    0.45
     révèle
    0.45
    ্যান্ড
    0.44
     faisant
    0.44
    Activations Density 0.000%

    No Known Activations