© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63117
    Prev
    Next
    INDEX
    Explanations

    self-addressed stamped envelopes

    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
     subsurface
    -0.77
     OPPORTUNITY
    -0.69
    chetta
    -0.69
     Fryer
    -0.69
     FLAG
    -0.69
     DISTR
    -0.68
     プリント
    -0.68
     Hawley
    -0.68
     zvuky
    -0.68
    representative
    -0.68
    POSITIVE LOGITS
     postage
    1.81
     prepaid
    1.67
     stamped
    1.52
     self
    1.23
     stamps
    1.18
     SAE
    1.15
     Postage
    1.14
     Stamp
    1.11
     Prepaid
    1.10
    addressed
    1.09
    Activations Density 0.020%

    No Known Activations