© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118434
    Prev
    Next
    INDEX
    Explanations

    code structure syntax

    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
    ));
    -1.20
    ()),
    -1.14
    .),
    -1.12
    '),
    -1.08
    ();
    -1.08
    )),
    -1.06
    ')),
    -1.00
    ());
    -0.99
     to
    -0.98
     while
    -0.98
    POSITIVE LOGITS
    }=
    1.29
    :
    1.29
     }=
    1.27
     }
    1.22
    ...}
    1.08
     =
    1.03
     }}=
    1.02
     =
    0.99
     _,
    0.97
    ograf
    0.96
    Activations Density 0.005%

    No Known Activations