© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    overall score

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

    key improvements and explanations

    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
    ര്‍ന്ന
    0.33
     {});
    0.32
    ),]),
    0.31
    getBlueTeam
    0.29
    tempCard
    0.28
    }),
    0.28
    ڑھ
    0.28
    ዣ
    0.28
    }`}>
    0.28
    咘
    0.27
    POSITIVE LOGITS
     Calculator
    0.42
     Calculation
    0.40
     CALCUL
    0.39
     calculation
    0.39
     calculator
    0.38
    計算
    0.38
     Calculate
    0.38
     calcular
    0.38
     Calculating
    0.37
     Calc
    0.37
    Activations Density 0.004%

    No Known Activations