© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7974
    Prev
    Next
    INDEX
    Explanations

    conditions and order

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

    sentiment and photo analysis

    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
    <\/
    0.57
    😨
    0.46
    🇼
    0.45
    🇷
    0.44
     🙂
    0.43
    ㄶ
    0.43
     👌
    0.41
    𐰼
    0.41
    ewnątrz
    0.40
    ంచరీలు
    0.40
    POSITIVE LOGITS
     indi
    1.79
     elec
    1.77
     posi
    1.77
     con
    1.70
     condi
    1.63
     poten
    1.63
     educa
    1.62
     com
    1.60
     construc
    1.60
     impor
    1.59
    Activations Density 0.129%

    No Known Activations