© 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. 6216
    Prev
    Next
    INDEX
    Explanations

    not fully

    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
     disproportion
    0.48
     cross
    0.47
    スの
    0.47
     CLEAR
    0.45
     dependence
    0.45
     dependency
    0.45
     simplistic
    0.45
     የ
    0.45
     backlash
    0.44
     проф
    0.44
    POSITIVE LOGITS
     menuju
    0.59
    ه
    0.51
    Nm
    0.50
    elesaikan
    0.50
     estará
    0.50
    गानिस्तान
    0.49
    divisor
    0.48
    UNIVERS
    0.48
     mengalami
    0.48
    㑹
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.