© 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. 46598
    Prev
    Next
    INDEX
    Explanations

    missing backpay

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

    fully a, more a, cannot provide, simply a

    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
     rufo
    0.51
    𝓰
    0.50
     hùng
    0.47
     underlined
    0.47
     endorph
    0.47
    PIT
    0.46
    BRAS
    0.46
     giường
    0.46
     Radford
    0.46
    PY
    0.46
    POSITIVE LOGITS
     }
    0.52
    enaar
    0.52
     }.
    0.49
    }-
    0.48
     }},
    0.47
    en
    0.46
    enska
    0.42
    }.
    0.42
    ]},
    0.42
    processing
    0.41
    Activations Density 0.000%

    No Known Activations