© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4307
    Prev
    Next
    INDEX
    Explanations

    stored or hidden away

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

    contained and hidden

    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_53_width_65k_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
     উপস্থিত
    0.49
     அடிப்ப
    0.44
     જોડ
    0.44
     напрямую
    0.44
    끊
    0.44
     THROUGH
    0.43
    ુલ
    0.41
    齬
    0.40
    雩
    0.40
     αι
    0.39
    POSITIVE LOGITS
     away
    1.11
     securely
    1.02
     tightly
    0.99
     Away
    0.93
     snugly
    0.91
     behind
    0.89
     safely
    0.88
    away
    0.88
    Away
    0.88
     someplace
    0.85
    Activations Density 0.153%

    No Known Activations