© 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. 8905
    Prev
    Next
    INDEX
    Explanations

    sorry for your loss

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

    often followed by description

    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
    ノ
    0.46
    blad
    0.46
    Ret
    0.44
    YOUR
    0.44
    S
    0.43
    C
    0.42
    ク
    0.42
    IPV
    0.42
    Mc
    0.41
    マ
    0.41
    POSITIVE LOGITS
     专业
    0.47
    ాన్
    0.46
     nourrice
    0.46
     conceivably
    0.45
     एक्चुअली
    0.44
    专业的
    0.43
     मगर
    0.42
     möglicherweise
    0.42
    硋
    0.41
     ankaŭ
    0.40
    Activations Density 0.001%

    No Known Activations