© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59579
    Prev
    Next
    INDEX
    Explanations

    age-appropriate material

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

    legacy or creation

    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_31_width_262k_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
    aidl
    0.50
    incidence
    0.49
    อย่างไร
    0.44
     হোমিওপ্যাথিক
    0.44
     ইরান
    0.44
    ناک
    0.44
     }}\
    0.43
    ]}{\
    0.43
     Bhosle
    0.42
     okun
    0.42
    POSITIVE LOGITS
     sustent
    0.49
    w
    0.44
    кли
    0.43
    ch
    0.43
    钝
    0.42
     germany
    0.40
     revêt
    0.40
     during
    0.39
     қар
    0.39
    ט
    0.39
    Activations Density 0.000%

    No Known Activations