© 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. 4693
    Prev
    Next
    INDEX
    Explanations

    goal being, reference to

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

    breakdown, explanations, examples

    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
     miteinander
    0.42
     মধ্যকার
    0.42
    abbe
    0.39
     对于
    0.38
     faptul
    0.38
     nonché
    0.38
     Zeitpunkt
    0.36
    }');
    0.36
    τικός
    0.36
    uy
    0.36
    POSITIVE LOGITS
     கூடிய
    0.84
     intact
    0.79
     ausgestattet
    0.76
    为例
    0.75
     caveats
    0.69
     impunity
    0.66
     caveat
    0.63
     attached
    0.63
     proviso
    0.60
     regards
    0.59
    Activations Density 0.410%

    No Known Activations