© 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. 155607
    Prev
    Next
    INDEX
    Explanations

    correct task

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

    configuration or calculator

    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
     н
    0.49
     ከፍተኛ
    0.47
    prisma
    0.45
    ggi
    0.44
     স্বপ্নের
    0.44
    msk
    0.44
     grass
    0.43
    utilisateur
    0.43
    gaon
    0.43
     dreaming
    0.42
    POSITIVE LOGITS
    }^{-}
    0.52
     racionais
    0.48
     discurso
    0.45
    }^{\#
    0.45
    లో
    0.44
     sebebi
    0.44
     estud
    0.43
     revistas
    0.43
    }$
    0.43
     enunciado
    0.43
    Activations Density 0.000%

    No Known Activations