© 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. 42569
    Prev
    Next
    INDEX
    Explanations

    now?

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

    technical terms and non-English words

    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
     $=
    0.45
    ≈
    0.44
    開始
    0.42
     stari
    0.42
    =
    0.41
     enggak
    0.41
    含む
    0.41
     puedes
    0.41
    決して
    0.41
    心
    0.40
    POSITIVE LOGITS
     allocation
    0.47
     sản
    0.45
     Allocation
    0.44
    फ्टर
    0.44
    لوم
    0.43
    േന
    0.43
    ította
    0.43
    ieuse
    0.43
    ôté
    0.43
     হস্তে
    0.42
    Activations Density 0.000%

    No Known Activations