© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 69243
    Prev
    Next
    INDEX
    Explanations

    street names and following words

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

    Please read important notes

    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
     na
    0.54
    و
    0.53
    اريخ
    0.50
    主题
    0.49
    ت
    0.49
    ي
    0.49
    డుగు
    0.46
    捞
    0.46
     ú
    0.46
    ეს
    0.46
    POSITIVE LOGITS
     নিদর্শন
    0.57
    रिडोर
    0.54
    ದ್ದರಿಂದ
    0.52
    ovariant
    0.50
    absorbing
    0.47
    ಸ್ತಕ
    0.47
    ITERATURE
    0.46
    identified
    0.46
    REFERENCE
    0.45
    rider
    0.45
    Activations Density 0.001%

    No Known Activations