© 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. 210772
    Prev
    Next
    INDEX
    Explanations

    site and work

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

    growth rate, no icing, waste, stability

    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
     depressions
    0.48
     yalnız
    0.47
     intram
    0.46
     Центра
    0.45
     голов
    0.45
    }$.
    0.45
    的天
    0.45
     ноябре
    0.44
    }$,
    0.44
    },
    0.44
    POSITIVE LOGITS
    dia
    0.55
    té
    0.53
    también
    0.52
    drv
    0.52
    puede
    0.51
    modelo
    0.49
    rende
    0.48
    mib
    0.48
    descricao
    0.47
    bl
    0.47
    Activations Density 0.001%

    No Known Activations