© 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. 78468
    Prev
    Next
    INDEX
    Explanations

    amplification and congratulations

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

    institutions, classes, structures, amplify

    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
     ١
    0.49
    КО
    0.45
     Skype
    0.44
     aktivieren
    0.44
     اروپا
    0.43
    యత్
    0.42
    SACTION
    0.42
     TextBox
    0.42
     HTC
    0.42
    ТР
    0.42
    POSITIVE LOGITS
     colet
    0.46
     amplification
    0.46
    Ampl
    0.45
    ሣ
    0.45
     lawmakers
    0.44
     disciplinary
    0.44
     Ari
    0.40
     amplifying
    0.40
    ampl
    0.40
     divisors
    0.40
    Activations Density 0.000%

    No Known Activations