© 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. 117751
    Prev
    Next
    INDEX
    Explanations

    biological names followed by 'are'

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

    Plakinastrella clathrata

    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
    名词
    0.47
    锺
    0.47
    电阻
    0.47
    集群
    0.46
     khúc
    0.45
    جنة
    0.45
     संयोजन
    0.45
     শহরের
    0.44
    vVertex
    0.44
    擷
    0.44
    POSITIVE LOGITS
     FX
    0.45
    ]
    0.45
    }
    0.44
    Che
    0.44
     Che
    0.44
     beast
    0.43
     rebel
    0.43
     Ch
    0.42
    elephant
    0.41
     Gif
    0.41
    Activations Density 0.000%

    No Known Activations