© 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. 17540
    Prev
    Next
    INDEX
    Explanations

    sudden design advertising short diagnosis

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

    sudden emergence or attack

    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
     નિ
    0.41
    removeClass
    0.41
     valid
    0.40
    粛
    0.40
    VALID
    0.39
    scss
    0.38
    шина
    0.38
     Resolución
    0.38
    valid
    0.38
    modelo
    0.37
    POSITIVE LOGITS
    突
    0.67
     đột
    0.51
    变的
    0.44
    변
    0.43
     nat
    0.42
     fly
    0.41
    飞
    0.41
     moles
    0.40
    厥
    0.40
    菈
    0.40
    Activations Density 0.000%

    No Known Activations