© 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. 7307
    Prev
    Next
    INDEX
    Explanations

    Not only

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

    not all / everyone

    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
    "${
    0.41
    роў
    0.38
     */;
    0.38
    ㅁ
    0.37
    यास
    0.37
     чём
    0.37
    为何
    0.36
    "_
    0.36
    <h5>
    0.36
     MainActivity
    0.36
    POSITIVE LOGITS
    surprisingly
    0.79
    every
    0.78
     every
    0.76
     surprisingly
    0.76
    everyone
    0.65
     everyone
    0.64
     Surprisingly
    0.63
     ogni
    0.62
    icing
    0.59
     mọi
    0.57
    Activations Density 0.033%

    No Known Activations