© 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. 62365
    Prev
    Next
    INDEX
    Explanations

    this fall or summer

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

    gender or folk music

    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
    ++]
    0.52
    ]
    0.51
     *.
    0.48
     corrosion
    0.48
     °
    0.48
    3
    0.47
     ^
    0.47
     <
    0.47
    IO
    0.47
    )
    0.47
    POSITIVE LOGITS
     एसोसिएशन
    0.49
    盯着
    0.47
     автобу
    0.46
    ර
    0.46
    Компания
    0.46
    笪
    0.46
     celebración
    0.46
    䍘
    0.45
     편리
    0.45
    ساس
    0.44
    Activations Density 0.000%

    No Known Activations