© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 10530
    Prev
    Next
    INDEX
    Explanations

    months and days

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

    code formatting elements

    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_40_width_16k_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
     }},
    0.54
     }}
    0.49
     self
    0.44
    '}}
    0.44
     Self
    0.43
     }}>
    0.43
    }},\
    0.42
    }});
    0.42
     }}=\
    0.41
            
    0.40
    POSITIVE LOGITS
    meters
    0.42
    ニュ
    0.40
     fasi
    0.39
    GLFW
    0.39
    ορ
    0.39
     પહો
    0.39
    azionali
    0.39
    ONI
    0.39
    RELATIVA
    0.38
    Avant
    0.38
    Activations Density 0.023%

    No Known Activations