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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1697
    Prev
    Next
    INDEX
    Explanations

    reporting speech

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

    tell or state information

    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
     தொடர்பான
    0.52
    粹
    0.48
     ويكيپيديا
    0.47
     있던
    0.47
    できた
    0.47
     connaissez
    0.46
     வந்த
    0.45
     "".
    0.45
     উঠেছিল
    0.45
    ၽ
    0.45
    POSITIVE LOGITS
     said
    3.39
    said
    3.14
     сказал
    2.77
     сказала
    2.66
     says
    2.52
     कहा
    2.44
     dijo
    2.44
     mengatakan
    2.44
     sagte
    2.41
     گفت
    2.36
    Activations Density 0.599%

    No Known Activations