© 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. 70007
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    Angular apps

    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
     ㅁ
    0.49
     Samaj
    0.49
     других
    0.48
     शेखर
    0.48
     ደቂ
    0.48
    ̧
    0.47
    uski
    0.47
    <unused277>
    0.47
     জনগোষ্ঠীর
    0.46
    <unused506>
    0.46
    POSITIVE LOGITS
     کیوں
    0.44
     decisões
    0.43
     reacts
    0.42
    隐含
    0.42
    error
    0.41
     yr
    0.41
     hasn
    0.40
     decisions
    0.40
     error
    0.40
     undecided
    0.40
    Activations Density 0.000%

    No Known Activations