© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117339
    Prev
    Next
    INDEX
    Explanations

    mathematical and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }=-
    -1.07
    )=-\
    -0.90
    )=-
    -0.87
    }=-\
    -0.85
    }<\
    -0.83
    mpz
    -0.82
    ]=-
    -0.82
    }^{*}$
    -0.81
    =_
    -0.79
    }:=
    -0.79
    POSITIVE LOGITS
    =(
    2.52
    ",(
    2.47
    ((
    2.31
     [(
    2.28
     ((
    2.20
     ${(
    2.20
    [(
    2.13
    ',(
    2.03
     =(
    2.02
    {(
    1.93
    Activations Density 0.067%

    No Known Activations