© 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. 97020
    Prev
    Next
    INDEX
    Explanations

    enrollment shifts, personal updates, time significantly

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

    patterns emerge

    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
    .
    0.53
    '
    0.50
    _
    0.50
    Bet
    0.48
    Mart
    0.47
    },
    0.46
     messages
    0.45
    ని
    0.44
    })
    0.44
    ご覧
    0.44
    POSITIVE LOGITS
    𒆪
    0.64
    esterly
    0.54
     বিদ্রোহ
    0.52
     नक
    0.50
     ಮುಂದ
    0.49
     fécond
    0.49
    ąg
    0.48
     conlle
    0.47
     Vorsitz
    0.47
     soweit
    0.47
    Activations Density 0.001%

    No Known Activations